Prof. Dr. rer. nat. Andreas Wendemuth
Prof. Dr. rer. nat. Andreas Wendemuth
Chair of Cognitive Systems
Current projects
Adaptive strategies for assistance technologies in multi-person interactions II (ASAMI II)
Duration: 31.12.2024 bis 31.12.2024
The overarching goals of ASAMI II are to understand the relationship between verbal dispositions and intentions to act, as well as the strategies of users of an assistance system in a multi-person situation. For this, the development, evaluation and optimization of the situation-related disposition recognition of the user through spoken language will remain in focus. This is expanded to include the component of recognizing action intentions in the dialogic environment. The evaluation of user characteristics is an important prerequisite for dialogue management. An informed disposition recognition is established, which is based on acoustic events, which can be derived from spectral, prosodic and paralinguistic features. The knowledge gained will flow directly into the recognition of action intentions and interaction style, which will be used for an adaptive, goal-oriented dialogue strategy. Complementary to this, the acoustic user signals are analyzed within a multi-person situation. For this purpose, the dynamic interplay between active and passive interaction parts (involvement) of a communication partner is analyzed on an acoustic level. Such dynamic changes are an integral feature of a conversation and provide information about the user's strategies. In particular, this interplay can be observed in a scenario consisting of an assistance system and several people. The focus here is on establishing adaptive problem-solving strategies.
Adaptive strategies for assistance technologies in multi-person interactions II (ASAMI II)
Duration: 01.07.2022 bis 31.12.2024
The overarching goals of ASAMI II are to understand the relationship between verbal dispositions and intentions to act, as well as the strategies of users of an assistance system in a multi-person situation. For this, the development, evaluation and optimization of the situation-related disposition recognition of the user through spoken language will remain in focus. This is expanded to include the component of recognizing action intentions in the dialogic environment. The evaluation of user characteristics is an important prerequisite for dialogue management. An informed disposition recognition is established, which is based on acoustic events, which can be derived from spectral, prosodic and paralinguistic features. The knowledge gained will flow directly into the recognition of action intentions and interaction style, which will be used for an adaptive, goal-oriented dialogue strategy. Complementary to this, the acoustic user signals are analyzed within a multi-person situation. For this purpose, the dynamic interplay between active and passive interaction parts (involvement) of a communication partner is analyzed on an acoustic level. Such dynamic changes are an integral feature of a conversation and provide information about the user's strategies. In particular, this interplay can be observed in a scenario consisting of an assistance system and several people. The focus here is on establishing adaptive problem-solving strategies.
NIIMO: Netzwerkinitiative Intelligente Mobilität
Duration: 01.01.2021 bis 31.12.2024
Mobilitätsbedürfnisse, verkehrsplanerische und verkehrswirtschaftliche Ansätze, Reallabors, in Kooperation mit NASA GmbH. Dies wird mit Kooperationsvertrag OVGU-NASA vom Februar 2021 verfolgt.
.
Completed projects
Intelligenter Mobilitätsraum Magdeburg
Duration: 01.01.2021 bis 31.12.2023
Die Otto-von-Guericke-Universität Magdeburg (Forschungsschwerpunkt Intelligenter Mobilitätsraum, Sprecher Prof. A. Wendemuth) und die Nahverkehrsservicegesellschaft Sachsen-Anhalt GmbH (NASA) schaffen gemeinsam in der Region Magdeburg einen Experimentierraum für Mobilitätslösungen. Dazu haben beide Seiten im Februar 2021 einen Kooperationsvertrag unterschrieben. Neue Ergebnisse und Technologien aus der Forschung werden für Mobilität & Leben/ Wohnen der Zukunft erprobt und umgesetzt. Praxisnah werden Alltagslösungen entwickelt, um Stadt und Umland besser miteinander zu vernetzen. Hier entstehen individualisierte Angebote sowohl für mobilitätseingeschränkte ältere Menschen wie auch für junge mobile Familien.
Adaptive Strategies for Assistance Technologies in Multi-Party-Interactions (ASAMI)
Duration: 01.01.2021 bis 30.06.2022
Adaptive strategies for assistance technologies in multi-party interactions (ASAMI) are support paradigms that can offer targeted technical assistance for individual or multiple actors in order to reduce uncertainty in action planning and in the joint interaction of the actors and to advance task processing. This includes anticipating and selecting options for action, monitoring and adapting the consequences of actions, strategies for obtaining information (external), situational exploration and communicative strategies such as feedback, informing, intervening or negotiating using means of multimodal, dialogic communication. Also included is the translation and creative linking of knowledge from other contexts in order to expand the scope of possibilities. Action-guiding objectives and plans of the actors are recorded and included.
Intentional, anticipatory, interactive systems (IAIS)
Duration: 01.01.2018 bis 31.12.2021
Intentional, anticipatory, interactive systems (IAIS) represent a new class of user-centered assistance systems and are a nucleus for the development of information technology with corresponding SMEs in Saxony-Anhalt. IAIS uses action and system intentions derived from signal data, and the affective state of the user. By anticipating the further action of the user, solutions are interactively negotiated. The active roles of humans and systems change strategically, which requires neurological and behavioral models. The human-machine-systems are being deployed in our systems lab, based on previous work in the SFB-TRR 62. The goal of lab tests is the understanding of the situated interaction. This supports the regional economy in their integration of assistance systems for Industry 4.0 in the context of demographic change.
ADAS&ME : Adaptive Advanced Driver Assistance Systems to support incapacitated drivers and Mitigate Effectively risks through tailor made Human Machine Interaction under automation
Duration: 01.09.2016 bis 28.02.2020
ADAS&ME will develop adapted Advanced Driver Assistance Systems that incorporate driver/rider state, situational/environmental context, and adaptive interaction to automatically transfer control between vehicle and driver/rider and thus ensure safer and more efficient road usage. The work is based around 7 Use Cases, covering a large proportion of driving on European roads. Experimental research will be carried out on algorithms for driver state monitoring as well as on Human-Machine-Interaction and automation transitions. Robust detection/prediction algorithms will be developed for driver/rider state monitoring towards different driver states, such as fatigue, sleepiness, stress, inattention and impairing emotions, employing existing and novel sensing technologies, taking into account traffic and weather conditions and personalizing them to individual driver s physiology and driving behavior. Further, the core development includes multimodal and adaptive warning and intervention strategies based on current driver state and severity of scenarios. The final outcome is a driver/rider state monitoring system, integrated within vehicle automation. The system will be validated with a wide pool of drivers/riders under simulated and real road conditions and under different driver/rider states. This challenging task has been undertaken by a multidisciplinary European Consortium of 30 Partners, including an original equipment manufacturer per vehicle type and 7 direct suppliers.
The Cognitive Systems Group at Otto-von-Guericke-University will contribute to this consortium by providing analysis of emotional content of acoustic utterances in the car. We will also engage in information fusion of data from various modalities (acoustic, video, and others) and analyzing this data for identifying markers for detecting drowsiness or a loss of control state of the driver, thus contributing to driver assistance in several use cases, such as cars, busses, trucks, and motorcycles.
3D Sensation
Duration: 01.01.2014 bis 31.12.2019
The alliance 3Dsensation gives machines the ability of the visual recording and interpretation of complex scenarios through innovative 3D technologies. Machines are situationally acting partners and personalized Wizard of Oz. The new form of human-machine interaction 3Dsensation manages access
to living and working environments regardless of age and physical fitness.
In the production 3Dsensation allows the symbiosis of man and machine on the basis of 3D vision. It creates a safe environment for people in manufacturing processes, ensuring the perception of assistance systems and ensures the quality of products.
Through the 3D collection and analysis of facial expressions, gestures and movement to control assistance systems 3Dsensation improve health care and guarantee self-determination into old age.
By coupling of 3D information with assistance systems 3Dsensation enables individual mobility independent of health and age-related impairments in urban and rural areas.
3Dsensation creates individual security by the autonomous experiential 3D analysis of characteristics of individuals and movements for the identification of problems and dangers.
By sector and interdisciplinary networking of science and industry an alliance is created, which solves key technical, ethical and sociological issues of human-machine interaction.
3Dsensation delivers fundamentally new solutions of human-machine interaction and thus secures the future for Germany's most important export industries.
MOD 3D (within 3Dsensation): Modelling of temporal sequences of behavior and action intentions from multimodal 3D-Data (Extended Project)
Duration: 01.01.2018 bis 31.12.2019
The alliance 3Dsensation provides machines, through innovative 3D technologies, with the ability of visual recording and interpretation of complex scenarios.
Consequently machines become situational acting partners and personalized human assistants.
This new form of human-machine interaction enables access to living and working environments, regardless of age and physical capacity.
MOD-3D is going to investigate modeling of temporal sequences of behavior and action intentions
from multimodal 3D-Data and to analyze prospective improvements with regards to that.
MOVA 3D (within 3Dsensation): Multimodal Omnidirectional 3D-Sensor for the Behaviour Analysis of Users
Duration: 01.08.2016 bis 31.12.2019
The alliance 3Dsensation provides machines, through innovative 3D technologies, with the ability of visual recording and interpretation of complex scenarios.
Consequently machines become situational acting partners and personalized human assistants.
This new form of human-machine interaction enables access to living and working environments, regardless of age and physical capacity.
MOVA3D realizes a novel multimodal omnidirectional 3D-Sensor for behavioural analyses of persons in ambient assisted living. Acoustic3D-Signals will be evaluated regarding situation und affectivity of the person.
MOD 3D (within 3Dsensation): Modelling of temporal sequences of behavior and action intentions from multimodal 3D-Data
Duration: 01.08.2015 bis 31.12.2017
The alliance 3Dsensation provides machines, through innovative 3D technologies, with the ability of visual recording and interpretation of complex scenarios.
Consequently machines become situational acting partners and personalized human assistants.
This new form of human-machine interaction enables access to living and working environments, regardless of age and physical capacity.
MOD-3D is going to investigate modeling of temporal sequences of behavior and action intentions
from multimodal 3D-Data and to analyze prospective improvements with regards to that.
www.uni-ulm.de/sfb-trr-62
Duration: 31.12.2016 bis 31.12.2017
Fusion of situation data from speech, gesture, mimics, and psychobiological data will give
advanced classification results. Multimodal information fusion architectures are generated.
SFB / Transregio 62: Recognition of emotion from speech
Duration: 31.12.2016 bis 31.12.2017
Emotions will be recognized from speech. Features are subsymbolic and biologically inspired. Emotion classes are being identified. Fusion with other information sources will give
advanced classification results. Intention recognition is a further goal. Emotional Speech will be provoked. Emotion-annotated data bases will be generated.
www.uni-ulm.de/sfb-trr-62
Duration: 31.12.2012 bis 31.12.2016
Fusionof situation data from speech, gesture, mimics, and psychobiological data will give
advanced classification results. Multimodal information fusion architectures are generated.
SFB / Transregio 62: Recognition of emotion from speech
Duration: 31.12.2012 bis 31.12.2016
Emotions will be recognized from speech. Features are subsymbolic and biologically inspired. Emotion classes are being identified. Fusion with other information sources will give
advanced classification results. Intention recognition is a further goal. Emotional Speech will be provoked. Emotion-annotated data bases will be generated.
SFB / Transregio 62: Central Coordination
Duration: 31.12.2012 bis 31.12.2016
Prof. Wendemuth ist the Magdeburg Speaker of the SFB / TRR 62 "A Companion-Technology for Cognitive Technical Systems". Central Coordination is responsible for Project Management, two labs in Ulm and Magdeburg are co-ordinated, 3 demonstration scenarios will be built at both sites, Wizard-of-Oz-trials are being conducted. A Graduate Colleg will be installed.
Emotion -based support for interactive applications in call centers
Duration: 15.04.2014 bis 28.11.2015
The application-oriented research in the field " emotion -based support for interactive applications in call centers " will be further developed. Here is the phone dialogue ,
in which the call center operator is supported in his conversation design through feedback on the
emotional state (control , valence ).
Category Theory for Disposition Recognition
Duration: 01.06.2013 bis 28.06.2014
Category theory is used to identify dispositions and matching features. Appraisals are the main unit for analysis. As a result, a consolidated feature basis is obtained.
Situationsangepasste Spracherkennung
Duration: 31.12.2012 bis 14.01.2014
Hier soll ein Situationsmodell genutzt werden, um top-down Durchgriff im Spracherkenner und Dialogmanager zu ermöglichen. Ziel ist, nicht nur (dichte) Lattices als Schnittstellen zu nutzen, sondern z.B. bei Änderung der akustischen Umgebung direkt die akustische Merkmalsextraktion zu adaptieren und iterativ den Spracherkenner neu zu nutzen. Ähnliches gilt für Änderungen im Emotions- oder Verhaltenszustand, die z.B. zur Nutzung angepasster akustischer Modelle führen. Oder Änderungen in der Domäne oder der Aufgabe, oder der Kooperativität oder der Intention des Benutzers, die den Dialogmanager beeinflussen. Lernvorgänge sind hier zu implementieren und zu untersuchen bzw. die Anzahl von Alternativen zu vergrößern. Aus der Spracherkennung sind abgeleitete Grössen zu definieren, die für Verhaltensmodelle elevant sind und von diesem interpretativ verwendet werden können bzw. dieses modifizieren.
Linguistic-Phonetic Analysis
Duration: 01.01.2013 bis 31.12.2013
We used textual transcripts to analyse interaction styles and discourse structures. Further, we model the subject's internal success state with a hidden Markov model trained using the observed sequences of system feedback. Aiming on automatic detection of specic subjects's reactions, we then semi-automatically annotate significant dialog events, i.e. phrases indicating an irregular, i.e. not-task-oriented subject behavior. We use both acoustic and linguistic features to build several trait-specic classiers for dialog phases.
Model for localisation of moods and personality traits in valence-pleasure-arousal-space
Duration: 01.01.2013 bis 31.12.2013
A Model for localisation of moods and personality traits in valence-pleasure-arousal-space is developed. Experimental trals are located in this space and a trajectory is modelled, which is mood- and personality dependent.
Context-Dependent Learning and Memory Modelling in Cognitive Behavioral Scenarios
Duration: 18.12.2012 bis 30.06.2013
Zwei Modelle des assoziativen und kontextabhängigen Lernens werden modelliert. Damit können Versuche mit menschlichen Probanden, welche Teil der Arbeit von Prof. Dr. Jochen Braun und der Doktorarbeit von Dipl.-Ing. Oussama Hamid sind , informationstechnisch nachvollzogen werden. Die beiden Modelle verfolgen jeweils zwei unterschiedliche Ansätze und wurden in Matlab implementiert.
Ein Ansatz zur Modellierung basiert auf einem Markov-Entscheidungsprozess (engl. Markov Decision Process), wie er häufig im Bereich des Maschinellen Lernens verwendet wird. Ein damit entworfener menschenähnlicher Lernalgorithmus wurde anschließend um die Fähigkeit erweitert aus dem Zeitkontext in der Lernaufgabe Nutzen zu ziehen.
Der zweite Ansatz ist ein Kapazitätsmodell, welches sich auf Erkenntnisse aus der Gedächtnispsychologie stützt. Das Lernen von Assoziationen wird als Prozess im Kurzzeitgedächtnis modelliert, wobei der zeitliche Kontext unterstützend wirkt. Die Kapazität des Kurzzeitspeichers ist dabei der limitierende Faktor. Die Rolle der zeitlichen Information wurde auf verschiedene Weisen in das Modell implementiert. Es kann z.B. ein Einfluss auf die Vergessensrate oder auf das Erinnerungsvermögen der Probanden simuliert werden. Für die Simulation von Umlernen bei Kontextwechsel wurde zusätzlich ein Langzeitgedächtnis in das Modell eingefügt.
informationstechnisch nachvollzogen werden. Die beiden Modelle verfolgen jeweils zwei unterschiedliche Ansätze und wurden in Matlab implementiert.
SFB / Transregio 62: Recognition of emotion from speech
Duration: 31.12.2008 bis 31.12.2012
Emotions will be recognized from speech. Features are subsymbolic and biologically inspired. Emotion classes are being identified. Fusion with other information sources will give
advanced classification results. Intention recognition is a further goal. Emotional Speech will be provoked. Emotion-annotated data bases will be generated.
www.uni-ulm.de/sfb-trr-62
Duration: 31.12.2008 bis 31.12.2012
Fusionof situation data from speech, gesture, mimics, and psychobiological data will give
advanced classification results. Multimodal information fusion architectures are generated.
SFB / Transregio 62: Central Coordination
Duration: 31.12.2008 bis 31.12.2012
Prof. Wendemuth ist the Magdeburg Speaker of the SFB / TRR 62 "A Companion-Technology for Cognitive Technical Systems". Central Coordination is responsible for Project Management, two labs in Ulm and Magdeburg are co-ordinated, 3 demonstration scenarios will be built at both sites, Wizard-of-Oz-trials are being conducted. A Graduate Colleg will be installed.
Context-Dependent Learning and Memory Modelling in Cognitive Behavioral Scenarios
Duration: 18.12.2008 bis 18.12.2012
Zwei Modelle des assoziativen und kontextabhängigen Lernens werden modelliert. Damit können Versuche mit menschlichen Probanden, welche Teil der Arbeit von Prof. Dr. Jochen Braun und der Doktorarbeit von Dipl.-Ing. Oussama Hamid sind , informationstechnisch nachvollzogen werden. Die beiden Modelle verfolgen jeweils zwei unterschiedliche Ansätze und wurden in Matlab implementiert.
Ein Ansatz zur Modellierung basiert auf einem Markov-Entscheidungsprozess (engl. Markov Decision Process), wie er häufig im Bereich des Maschinellen Lernens verwendet wird. Ein damit entworfener menschenähnlicher Lernalgorithmus wurde anschließend um die Fähigkeit erweitert aus dem Zeitkontext in der Lernaufgabe Nutzen zu ziehen.
Der zweite Ansatz ist ein Kapazitätsmodell, welches sich auf Erkenntnisse aus der Gedächtnispsychologie stützt. Das Lernen von Assoziationen wird als Prozess im Kurzzeitgedächtnis modelliert, wobei der zeitliche Kontext unterstützend wirkt. Die Kapazität des Kurzzeitspeichers ist dabei der limitierende Faktor. Die Rolle der zeitlichen Information wurde auf verschiedene Weisen in das Modell implementiert. Es kann z.B. ein Einfluss auf die Vergessensrate oder auf das Erinnerungsvermögen der Probanden simuliert werden. Für die Simulation von Umlernen bei Kontextwechsel wurde zusätzlich ein Langzeitgedächtnis in das Modell eingefügt.
informationstechnisch nachvollzogen werden. Die beiden Modelle verfolgen jeweils zwei unterschiedliche Ansätze und wurden in Matlab implementiert.
Situationsangepasste Spracherkennung
Duration: 10.10.2007 bis 09.10.2012
Hier soll ein Situationsmodell genutzt werden, um top-down Durchgriff im Spracherkenner und Dialogmanager zu ermöglichen. Ziel ist, nicht nur (dichte) Lattices als Schnittstellen zu nutzen, sondern z.B. bei Änderung der akustischen Umgebung direkt die akustische Merkmalsextraktion zu adaptieren und iterativ den Spracherkenner neu zu nutzen. Ähnliches gilt für Änderungen im Emotions- oder Verhaltenszustand, die z.B. zur Nutzung angepasster akustischer Modelle führen. Oder Änderungen in der Domäne oder der Aufgabe, oder der Kooperativität oder der Intention des Benutzers, die den Dialogmanager beeinflussen. Lernvorgänge sind hier zu implementieren und zu untersuchen bzw. die Anzahl von Alternativen zu vergrößern. Aus der Spracherkennung sind abgeleitete Grössen zu definieren, die für Verhaltensmodelle elevant sind und von diesem interpretativ verwendet werden können bzw. dieses modifizieren.
Speech Recognition with confidence assessment
Duration: 01.04.2008 bis 31.03.2012
Combining Modalities (with confidences) on the feature stream. Probabilistic Theory for thecorrect evaluation of the overall best hypothesis.
wdok.cs.uni-magdeburg.de/nimitek
Duration: 01.05.2008 bis 31.12.2010
The project NIMITEK II adresses man-machine interaction. Neurobiological models will be generated by partners in Magdeburg, and will be used for modelling emotion and intention recognition which will in turn improve the user-friendliness of the machine system. Conversely, the technical system will be a test bed for neurological and behavioral research. Prof. Dr. Wendemuth is coordinator of the NIMITEK consortium. In his group, particular research aspects of the project are speech and prosody recognition, multimodal information extraction, classification of emotional units, modelling of associative coherence.
Bernstein-Gruppe Components of cognition: small networks to flexible rules: Multi-modal emotion recognition and blind source separation
Duration: 15.12.2006 bis 31.01.2010
The overarching questions to be addressed by this project are as follows:
- Is the learning of context-conditional associations by human observers influenced by, or even predicated on, consistent temporal ordering of environmental events? In other words, can the context-dependence of human associative learning be understood in terms of a temporalorderdependence?
- How does temporal-order-dependent learning compare to abstract learning algorithms (e.g.,support-vector machines, dynamic adaptation of neural nets) for detecting patterns and regularities in high-dimensional data streams?
- Is temporal-order-dependent learning suited as a general solution to complex learning problems? How does it perform on diverse problems such as those described in section 7.3 (i.e., learning to recognize prosodic signals in speech or emotional markers in facial expression)?
www.bernstein-zentren.de/
Duration: 15.12.2006 bis 31.01.2010
The immediate goal is to analyze concurrent speech utterances and facial expressions in terms of speaker emotion and intention. Speech and face information will be combined to a multi-modal feature vector and subjected to blind source separation (ICA) analysis. In a different context similar methods were already suggested by the applicant in his Habilitationsschrift [Michaelis 80]. In the longer term, the proposed project is aimed at the automatic recognition of subtly different human interactions (e.g., friendly/cooperative, impatient/evasive, aversive/violent). A second long-term goal is to apply the automatic recognition of emotion states to a neurobiological investigation of the neural basis of emotion. A correlation with results of EEG and MRI investigations can be carried out [Heinzel 05]. The software tools to be developed here would be invaluable in brain imaging (fMRI) of human emotion.interactions (e.g., friendly/cooperative, impatient/evasive, aversive/violent). A second long-term goalis to apply the automatic recognition of emotion states to a neurobiological investigation of the neuralbasis of emotion. A correlation with results of EEG and MRI investigations can be carried out[Heinzel 05]. The software tools to be developed here would be invaluable in brain imaging (fMRI) ofhuman emotion.
Situationsangepasste, biologische Verhaltensmodellierung
Duration: 10.10.2007 bis 10.01.2010
Hier sollen das Situationsmodell und Ergebnisse des iterativen, einander modifizierenden top-down und bottom-up Prozesses in der Spracherkennung (Projekt Situationsangepasste Spracherkennung) genutzt werden, um ein interpretatives Verhaltensmodell einer Person oder von Personen in einer definierten Situation / Umgebung ( Situiertheit ) zu erzeugen und damit Interaktion als (intentionales) Verhalten zu modellieren. Die Ergebnisse des Projektes Situationsangepasste Spracherkennung dienen hier als direktes Maß dafür, wie sich die Person(en) zur Umgebung und zu einer gestellten Aufgabe äußern (Inhalt, Emotion) und wie dies mit den erfassten Umgebungsparametern zusammenpasst (match / mismatch der sprachlichen Äusserungen zur Umgebung), woraus Bestätigungen oder Änderungen des Verhaltensmodells abgeleitet werden können. Das gleiche gilt für eine Intentionserkennung, die mit B.Vlasenko zusammen entwickelt wird. Für die Situationsbeschreibung sind insbesondere Modellgrössen wie Zustandsparameter, Ziel(Kosten)grössen, Optimierungskriterien (LQ, ML, MMI, ME, MDL, andere?) zu definieren. Iterative und/oder syntaktisch-deskriptive (wenn-dann-Beziehungen) Lernvorgänge sind hier zu implementieren und zu untersuchen bzw. die Anzahl von Alternativen zu vergrößern. Das umfasst sowohl die Fähigkeit zum besseren Lernen einer Situation wie auch das Lernen, zwischen verschiedenen Situationen zu unterscheiden (dies ist auch in der Gruppe Prof. Braun von hohem Interesse). Aus dem Verhaltensmodell sind abgeleitete Grössen zu definieren, die für die Spracherkennung und Dialogmanager relevant sind und von dieser interpretativ verwendet werden können bzw. diesen modifizieren.
www.iesk.ovgu.de/kog__systeme-p-1907/hauptmenue/mitarbeiter/kinfe_tadesse_mengistu.html
Duration: 01.08.2008 bis 30.04.2009
This proposal is about using speech technology for the purpose of adding data to and requesting information from a remote database via telephone. Speech input to a data base is handled by automatic speech recognition technology while speech output is handled by speech synthesis technology. Inline with these two technologies, there are two major processes that are essential: speech understanding and response generation. Automatic speech recognition is not speech understanding, i.e., there is no linguistic or semantic analysis performed. In order to do live interaction with a remote database via telephone speech understanding is vitally important. Similarly speech synthesis cannot decide what to say by itself, therefore the response generation part should provide what is to be said by the speech synthesizer.
Robust Remote Speech Recognition Database Access via Telephone
Duration: 01.08.2005 bis 31.07.2008
This proposal is about using speech technology for the purpose of adding data to and requesting information from a remote database via telephone. Speech input to a data base is handled by automatic speech recognition technology while speech output is handled by speech synthesis technology. Inline with these two technologies, there are two major processes that are essential: speech understanding and response generation. Automatic speech recognition is not speech understanding, i.e., there is no linguistic or semantic analysis performed. In order to do live interaction with a remote database via telephone speech understanding is vitally important. Similarly speech synthesis cannot decide what to say by itself, therefore the response generation part should provide what is to be said by the speech synthesizer.
Usage of Support-Vector-Machines for flexible incorporationin automatic speech recognition.
Duration: 01.07.2003 bis 29.06.2008
Support-Vector-Machines are used for flexible tailoringof automatic speech recognition systems to new tasks.
Neurobiologisch inspirierte, multimodale Intentionserkennung für technische Kommunikationssysteme II
Duration: 01.01.2008 bis 01.04.2008
The project NIMITEK II adresses man-machine interaction. Neurobiological models will be generated by partners in Magdeburg, and will be used for modelling emotion and intention recognition which will in turn improve the user-friendliness of the machine system. Conversely, the technical system will be a test bed for neurological and behavioral research. Prof. Dr. Wendemuth is coordinator of the NIMITEK consortium. In his group, particular research aspects of the project are speech and prosody recognition, multimodal information extraction, classification of emotional units, modelling of associative coherence.
Neurobiologically inspired, multimodal Intention Recognition for technical communication systems
Duration: 01.12.2005 bis 31.12.2007
The project NIMITEK adresses man-machine interaction. Neurobiological models will be generated by partners in Magdeburg, and will be used for modelling emotion and intention recognition which will in turn improve the user-friendliness of the machine system. Conversely, the technical system will be a test bed for neurological and behavioral research. Prof. Dr. Wendemuth is coordinator of the NIMITEK consortium. In his group, particular research aspects of the project are speech and prosody recognition, multimodal information extraction, classification of emotional units, modelling of associative coherence.
iesk.et.uni-magdeburg.de/KO/krueger/index.html
Duration: 01.10.2006 bis 31.12.2007
Support-Vector-Machines and Kernel-based Methods will be utilized in automatic speech recognition. Numercial Methods will be used to generate probability measures.
Support Vector Machines as acoustic models in Hidden-Markov-Model-based speech recognition systems.
Duration: 01.07.2003 bis 30.06.2007
Support Vector Machines are used to model Production probabilitieswhich are used as acoustic models in automatic speech recognition.
iesk.et.uni-magdeburg.de/KO/katz/index.html
Duration: 01.07.2006 bis 30.12.2006
In this dissertation, various parametric estimation methods in automatic speech recognition are researched.The aim is to develop estimation methods with high generalisation ability in speech recognition, in particular with few or mismatching data,as well as with disturbances by noise, channel etc. The work is both theoretical and software-oriented.
Support-Vector-Machines and Kernel-based Methods in automatic speech recognition
Duration: 01.10.2001 bis 30.09.2006
Support-Vector-Machines and Kernel-based Methods will be utilized in automatic speech recognition. Numercial Methods will be used to generate probability measures.
Generalisation in acoustic classifikation in automatic speech recognition.
Duration: 01.07.2001 bis 30.06.2006
In this dissertation, various parametric estimation methods in automatic speech recognition are researched.The aim is to develop estimation methods with high generalisation ability in speech recognition, in particular with few or mismatching data,as well as with disturbances by noise, channel etc. The work is both theoretical and software-oriented.
Iterative solution for a Multi-Class Discriminant analysis with kernel functions.
Duration: 01.07.2005 bis 30.06.2006
In robust speech recognition, phonetic units in signal space will be identified as belonging to one class. To ensure class separability, methods from digital signal processing wil be used. The new approach willtransform data implicitely into a high dimensionalfeature space, however only kernels will haveto be computed. Large matrix inversions will have to be done iteratively.
Iterative solution for a Multi-Class Discriminant analysis with kernel functions.
Duration: 01.07.2003 bis 30.06.2005
In robust speech recognition, phonetic units in signal space will be identified as belonging to one class. To ensure class separability, methods from digital signal processing wil be used. The new approach willtransform data implicitely into a high dimensionalfeature space, however only kernels will haveto be computed. Large matrix inversions will have to be done iteratively.
International Summer School: Robust Methods in Automatic Speech Recognition, 07.07.-18.07.2003
Duration: 07.04.2003 bis 18.07.2003
The summer school will:- provide concise methodological knowledge on speech recognition techniques to young researchers who have not yet had in-depth experience in the field- provide in-depth knowledge of robust methods - have young researchers apply their attained knowledge immediately in existing speech recognition software systems- enable young researchers to design their individual speech recognition application, in their own language on existing corpora- open up contacts to other academic institutions and industry through invited lecturers and application-oriented collaborations on site
International Summer University Automatic Speech Recognition 2002
Duration: 01.07.2002 bis 01.10.2002
Participants will take part in lecture and lab courses in Digital Signal Processing and Speech Recognition. They will then apply their knowledge within the speech recognition computer lab installed at the groups premises. Here, Texas Instruments Digital Signal Processors, Matlab tools for digital signal processing, and the Hidden Markov Toolkit (HTK) for speech recognition is available and running. Students will work in close collaboration with group members on state-of-the-art problems in digital signal processing and speech recognition. Results of their work will be integrated into the groups architecture.
2023
Book chapter
Cross-reliability benchmark test for preserving emotional content in speech-synthesis related datasets
Hintz, Jan; Wendemuth, Andreas; Siegert, Ingo
In: Elektronische Sprachsignalverarbeitung 2023 / Konferenz Elektronische Sprachsignalverarbeitung , 2023 - Dresden : TUDpress ; Draxler, Christoph *1960-*, S. 64-72 - (Studientexte zur Sprachkommunikation; 105)
Companion technology
Wendemuth, Andreas
In: Handbook of human-machine systems - Wiley ; Fortino, Giancarlo . - 2023, S. 155-163
Multiparty dialogic processes of goal and strategy formation in hybrid teams
Wendemuth, Andreas; Kopp, Stefan
In: Computer-Human Interaction Research and Applications , 1st ed. 2023. - Cham : Springer Nature Switzerland ; da Silva, Hugo Plácido, S. 110-120 - (Communications in computer and information science; volume 1996)
Cross-timescale experience evaluation framework for productive teaming
Raake, Alexander; Broll, Wolfgang; Chuang, Lewis L.; Domahidi, Emese; Wendemuth, Andreas
In: Engineering for a changing world - Ilmenau : ilmedia ; Sattler, Kai-Uwe *1968-* . - 2023, S. 1-6, Artikel 5.4.129
Going one step further: towards cognitively enhanced problem-solving teaming agents
Puricelli, Leonardo; Brandenburg, Stefan; Wendemuth, Andreas; Husung, Stephan; Armbruster, Diana; Meyer, Bertolt; Ragni, Marco
In: Engineering for a changing world - Ilmenau : ilmedia ; Sattler, Kai-Uwe *1968-* . - 2023, S. 1-12, Artikel 5.1.137
Presenting a German dataset of wake words - first analyses and comparison of different solutions for speech-based activation techniques
Busch, Matthias; Sinha, Yamini; Hintz, Jan; Wendemuth, Andreas; Siegert, Ingo
In: DAGA 2023 - Berlin : Deutsche Gesellschaft für Akustik e.V., S. 1478-1481
Dissertation
An automatic and multi-modal system for continuous pain intensity monitoring based on analyzing data from five sensor modalities
Othman, Ehsan; Hamadi, Ayoub; Wendemuth, Andreas
In: Magdeburg: Universitätsbibliothek, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Elektrotechnik und Informationstechik 2023, 1 Online-Ressource (xxi, 155 Seiten, 7,42 MB) [Literaturverzeichnis: Seite 137-155]
2022
Book chapter
Why Eli Roth should not use TTS-Systems for anonymization
Sinha, Yamini; Hintz, Jan; Busch, Matthias; Polzehl, Tim; Haase, Matthias; Wendemuth, Andreas; Siegert, Ingo
In: 2nd Symposium on Security and Privacy in Speech Communication - Incheon, Korea, 23-24 September 2022 - Internatinal Speech Communication Association ; Siegert, Ingo, S. 17-22
Emotion preservation for one-shot speaker anonymization using McAdams
Sinha, Yamini; Wendemuth, Andreas; Siegert, Ingo
In: Konferenz: 33. Konferenz "Elektronische Sprachsignalverarbeitung", Sonderborg, 2.-4. März 2022, Elektronische Sprachsignalverarbeitung 2022 - Dresden: TUDpress; Weston, Heather . - 2022, S. 235-242 - (Studientexte zur Sprachkommunikation; 103)
Parameter optimization issues for cross-corpora emotion classification
Vlasenko, Bogdan; Philippou-Hübner, David; Wendemuth, Andreas
In: Konferenz: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction, Geneva, Switzerland, 02-05 September 2013, Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII), 2013 - Piscataway, NJ: IEEE . - 2013, S. 454-459
Peer-reviewed journal article
Acoustic-based automatic addressee detection for technical systems - a review
Siegert, Ingo; Weißkirchen, Norman; Wendemuth, Andreas
In: Frontiers in computer science - Lausanne : Frontiers Media, Bd. 4 (2022), Artikel 831784, insges. 20 S.
Dissertation
Driver affect recognition from real-world speech data in in-vehicle driving environments
Requardt, Alicia Flores; Wendemuth, Andreas; Jumar, Ulrich
In: Magdeburg: Universitätsbibliothek, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Elektrotechnik und Informationstechnik 2022, 1 Online-Ressource (xxiii, 296 Seiten, 8,08 MB) [Literaturverzeichnis: Seite 209-251]
Article in conference proceedings
Public interactions with voice assistant - discussion of different one-shot solutions to preserve speaker privacy
Siegert, Ingo; Sinha, Yamini; Winkelmann, Gino; Jokisch, Oliver; Wendemuth, Andreas
In: Proceedings of the LREC 2022 Joint Workshop on Legal and Ethical Issues in Human Language Technologies and Multilingual De-Identification of Sensitive Language Resources (LEGAL - MDLR 2022) - Paris : European Language Resources Association (ELRA) ; Rigault, Mickaël, S. 44-47
2021
Peer-reviewed journal article
Admitting the addressee detection faultiness of voice assistants to improve the activation performance using a continuous learning framework
Siegert, Ingo; Weißkirchen, Norman; Krüger, Julia; Akhtiamov, Oleg; Wendemuth, Andreas
In: Cognitive systems research - Amsterdam [u.a.] : Elsevier Science, Bd. 70 (2021), S. 65-79
Dissertation
Efficient deep learning algorithms for securing Industrial Control Systems from cyberattacks
Potluri, Sasanka; Diedrich, Christian; Wendemuth, Andreas
In: Magdeburg, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Elektrotechnik und Informationstechnik 2021, xxviii, 268 Seiten [Literaturverzeichnis: Seite 181-194][Literaturverzeichnis: Seite 181-194]
2020
Book chapter
Investigation of the influence of standing waves on distant speech emotion recognition
Höbel-Müller, Juliane; Siegert, Ingo; Gottschalk, Martin; Heinemann, Ralph; Wendemuth, Andreas
In: Fortschritte der Akustik - DAGA 2020 - Berlin : Deutsche Gesellschaft für Akustik e.V. (DEGA), S. 822-825 [Konferenz: DAGA 2020, Hannover, 16.-19. März 2020]
Machine learning-assisted affect labelling of speech data
Requardt, Alicia Flores; Egorow, Olga; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2020 - Tagungsband der 31. Konferenz Magdeburg : Magdeburg, 4.-6. März 2020: Tagungsband der 31. Konferenz Magdeburg : Magdeburg, 4.-6. März 2020/ Konferenz "Elektronische Sprachsignalverarbeitung" - Dresden: TUDpress . - 2020, S. 199-205 - (Studientexte zur Sprachkommunikation; 95)
Filtering-based analysis of spectral and temporal effects of room modes on low-level descriptors of emotionally coloured speech
Gottschalk, Martin; Höbel-Müller, Juliane; Siegert, Ingo; Verhey, Jesko L.; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2020 - Tagungsband der 31. Konferenz Magdeburg : Magdeburg, 4.-6. März 2020 / Konferenz "Elektronische Sprachsignalverarbeitung" , 2020 - Dresden : TUDpress ; Wendemuth, Andreas, S. 219-226 - (Studientexte zur Sprachkommunikation; 95) [Konferenz: 31. Konferenz "Elektronische Sprachsignalverarbeitung", Magdeburg, 4.-6. März 2020]
Recognition performance of selected speech recognition APIs - a longitudinal study
Siegert, Ingo; Sinha, Yamini; Jokisch, Oliver; Wendemuth, Andreas
In: Speech and Computer - Cham : Springer ; Karpov, Alexey . - 2020, S. 520-529 - ( Lecture notes in computer science; 12335)
Towards true artificial peers
Weißkirchen, Norman; Böck, Ronald; Wendemuth, Andreas
In: Proceedings of the 2020 IEEE International Conference on Human-Machine Systems (ICHMS): Sept 7-9, 2020, Rome, Italy/ IEEE International Conference on Human-Machine Systems - [Piscataway, NJ]: IEEE . - 2020, insges. 5 S.
Utilizing computer vision algorithms to detect and describe local features in images for emotion recognition from speech
Weißkirchen, Norman; Reddy, Mainampati Vasudeva; Wendemuth, Andreas; Siegert, Ingo
In: Proceedings of the 2020 IEEE International Conference on Human-Machine Systems (ICHMS): Sept 7-9, 2020, Rome, Italy/ IEEE International Conference on Human-Machine Systems - [Piscataway, NJ]: IEEE; Weibkirchen, Norman . - 2020, insges. 6 S.
Peer-reviewed journal article
Towards affect-aware vehicles for increasing safety and comfort - recognising driver emotions from audio recordings in a realistic driving study
Requardt, Alicia F.; Ihme, Klas; Wilbrink, Marc; Wendemuth, Andreas
In: IET intelligent transport systems/ Institution of Engineering and Technology - London: IET, Bd. 14 (2020), 10, S. 1265-1277
Adaptive transitions for automation in cars, trucks, busses and motorcycles
Wendemuth, Andreas; Diederichs, Frederik; Knauss, Alessia; Milbrink, Marc; Lilis, Yannis; Chrysochoou, Evangelia; Annund, Anna; Bekiaris, Evangelos; Nikolaou, Stella; Finer, Svitlana; Zanovello, Luca; Maroudis, Pantelis; Krupenia, Stas; Abser, Andreas; Dimokas, Nikos; Apoy, Camilla; Karlsson, Johan; Larsson, Annika; Zidianakis, Emmanouil; Efa, Alexander; Widlroither, Harald; Dai, Mengnuo; Teichmann, Daniel; Sanatnama, Hamid; Bischoff, Sven
In: IET intelligent transport systems/ Institution of Engineering and Technology - London: IET . - 2020
Dissertation
Accessing the interlocutor - recognition of interaction-related interlocutor states in multiple modalities
Egorow, Olga; Wendemuth, Andreas; Diedrich, Christian
In: Magdeburg, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Elektrotechnik und Informationstechnik 2020, I, xv, 143 Seiten [Literaturverzeichnis: Seite 117-143][Literaturverzeichnis: Seite 117-143]
Habilitation
Anticipate the user - multimodal analyses in human-machine interaction towards group interactions
Böck, Ronald; Wendemuth, Andreas
In: Dresden: TUDpress, 2020, xxiii, 354 Seiten, Illustrationen, Diagramme, 24 cm - (Studientexte zur Sprachkommunikation; Band 98)
Editor
Elektronische Sprachsignalverarbeitung 2020 - Tagungsband der 31. Konferenz Magdeburg : Magdeburg, 4.-6. März 2020
Wendemuth, Andreas; Böck, Ronald; Siegert, Ingo
In: Dresden: TUDpress, 2020, XI, 288 Seiten, Illustrationen, Diagramme, 24 cm x 17 cm - (Studientexte zur Sprachkommunikation; Band 95)
2019
Abstract
Experimentelles Design zur Induktion von Emotionalität in Sprache und Gangverhalten im häuslichen Umfeld
Höbel-Müller, Juliane; Böck, Ronald; Perez Grassi, Ana Cecilia; Wendemuth, Andreas
In: 8. Interdisziplinärer Workshop Kognitive Systeme: Verstehen, Beschreiben und Gestalten Kognitiver (Technischer) Systeme: Duisburg, 26.-28. März 2019 - Duisburg: Universität Duisburg-Essen, 2019; Eyssel, Friederike . - 2019, S. 22-23
Admitting the addressee-detection faultiness to improve the performance using a continous learning framework
Siegert, Ingo; Weißkirchen, Norman; Wendemuth, Andreas
In: 8. Interdisziplinärer Workshop Kognitive Systeme: Verstehen, Beschreiben und Gestalten Kognitiver (Technischer) Systeme - Duisburg: Universität Duisburg-Essen, S. 38-39, 2019
Book chapter
Towards cognitive systems for assisted cooperative processes of goal finding and strategy change
Wendemuth, Andreas; Kopp, Stefan
In: Konferenz: IEEE International Conference on Systems, Man, and Cybernetics, IEEE SMC 2019, 6-9 October 2019, Bari Italy, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)/ IEEE International Conference on Systems, Man, and Cybernetics - [Piscataway, NJ]: IEEE . - 2019, S. 4302-4307
The Restaurant Booking Corpus - content-identical comparative human-human and human-computer simulated telephone conversations
Siegert, Ingo; Nietzold, Jannik; Heinemann, Ralph; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2019 - Dresden: TUDpress, S. 126-133 - (Studientexte zur Sprachkommunikation; 93)[Konferenz: 30. Konferenz Elektronische Sprachsignalverarbeitung 2019, Dresden, 6.-8. März 2019]
Analysis of the influence of different room acoustics on acoustic emotion features
Höbel-Müller, Juliane; Siegert, Ingo; Heinemann, Ralph; Requardt, Alicia Flores; Tornow, Michael; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2019: Tagungsband der 30. Konferenz, Dresden, 6.-8. März 2019 / Peter Birkholz und Simon Stone (Hrsg.): Tagungsband der 30. Konferenz, Dresden, 6.-8. März 2019/ Konferenz "Elektronische Sprachsignalverarbeitung" - Dresden: TUDpress, 2019 . - 2019, S. 156-163 - (Studientexte zur Sprachkommunikation; 93)[Konferenz: 30. Konferenz Elektronische Sprachsignalverarbeitung 2019: Tagungsband der 30. Konferenz, Dresden, 6.-8. März 2019 / Peter Birkholz und Simon Stone (Hrsg.), Dresden, 6.-8. März 2019]
Analysis of the influence of different room acoustics on acoustic emotion features and emotion recognition performance
Höbel-Müller, Juliane; Siegert, Ingo; Heinemann, Ralph; Requardt, Alicia Flores; Tornow, Michael; Wendemuth, Andreas
In: Tagungsband - DAGA 2019 - Berlin: Deutsche Gesellschaft für Akustik e.V. (DEGA), 2019 . - 2019, S. 886-889[Tagung: 45. Jahrestagung für Akustik, DAGA 2019, 18.-21. März 2019, Rostock]
Anticipating the user - acoustic disposition recognition in intelligent interactions
Böck, Ronald; Egorow, Olga; Höbel-Müller, Juliane; Requardt, Alicia Flores; Siegert, Ingo; Wendemuth, Andreas
In: Innovations in big data mining and embedded knowledge - Cham, Switzerland: Springer, 2019; Esposito, Anna . - 2019, S. 203-233 - (Intelligent systems reference library; volume 159)
Employing Bottleneck and convolutional features for speech-based physical load detection on limited data amounts
Egorow, Olga; Mrech, Tarik; Weißkirchen, Norman; Wendemuth, Andreas
In: Interspeech 2019: 15-19 September 2019, Graz - International Speech and Communication Association, 2019; Kubin, Gernot . - 2019, S. 1666-1670[Interspeech 2019, Graz, 15-19 September 2019]
Peer-reviewed journal article
On emotions as features for speech overlaps classification
Egorow, Olga; Wendemuth, Andreas
In: IEEE transactions on affective computing/ Institute of Electrical and Electronics Engineers - New York, NY: IEEE, 2010 . - 2019[Online first]
2018
Book chapter
Emotion recognition from disturbed speech - towards affective computing in real-world in-car environments
Lotz, Alicia Flores; Faller, Fabian; Siegert, Ingo; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2018: Tagungsband der 29. Konferenz, Ulm, 7.-9. März 2018/ Konferenz "Elektronische Sprachsignalverarbeitung"- Dresden: TUDpress, 2018, S. 208-215[Konferenz: 29. Elektronische Sprachsignalverarbeitung 2018, Ulm, 7. - 10. März; Literaturverzeichnis: Seite 214-215]
Significance of feature differences in the distinction of mental-load
Weißkirchen, Norman; Böck, Ronald; Wendemuth, Andreas; Nürnberger, Andreas
In: SMC 2018 / IEEE International Conference on Systems, Man, and Cybernetics , 2018 - Piscataway, NJ : IEEE ; Hata, Yutaka, S. 2604-2609 [Konferenz: 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC, Miyazaki, Japan, 7-10 October 2018]
Intention-based anticipatory interactive systems
Wendemuth, Andreas; Böck, Ronald; Nürnberger, Andreas; Hamadi, Ayoub; Brechmann, André; Ohl, Frank W.
In: SMC 2018: 2018 IEEE International Conference on Systems, Man, and Cybernetics$d7-10 October 2018, Miyazaki, Japan : proceedings/ IEEE International Conference on Systems, Man, and Cybernetics - Piscataway, NJ: IEEE, 2018; Hata, Yutaka . - 2018, S. 2579-2584[Konferenz: 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC, Miyazaki, Japan, 7-10 October 2018]
Improving emotion recognition performance by random-forest-based feature selection
Egorow, Olga; Siegert, Ingo; Wendemuth, Andreas
In: Speech and computer: 20th International Conference, SPECOM 2018, Leipzig, Germany, September 18-22, 2018 : proceedings/ SPECOM - Cham: Springer, 2018 . - 2018, S. 134-144 - (Lecture notes in computer science; 11096; Lecture notes in artificial intelligence)[Konferenz: 20th International Conference Speech and Computer, SPECOM 2018, Leipzig, Germany, September 18-22, 2018]
Recognition of emotional speech with convolutional neural networks by means of spectral estimates
Weißkirchen, Norman; Böck, Ronald; Wendemuth, Andreas
In: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW): 23-26 Oct. 2017/ International Workshop on Context Based Affect Recognition - [Piscataway, NJ]: IEEE, 2017; International Workshop on Context Based Affect Recognition (5.:2017) . - 2018, S. 50-55[Copyright: 2017; Konferenz: Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW, San Antonio, Tex., 23 - 26 October 2017]
Recognizing behavioral factors while driving - a real-world multimodal corpus to monitor the drivers affective state
Lotz, Alicia Flores; Ihme, Klas; Charnoz, Audrey; Maroudis, Pantelis; Dmitriev, Ivan; Wendemuth, Andreas
In: LREC 2018 - Paris : European Language Resources Association, ELRA, S. 1589-1596
The effect of emotional speech on relative speaker discrimination
Höbel-Müller, Juliane; Böck, Ronald; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2018: Tagungsband der 29. Konferenz, Ulm, 7.-9. März 2018/ Konferenz "Elektronische Sprachsignalverarbeitung" - Dresden: TUDpress, 2018; Berton, André . - 2018, S. 216-223[Konferenz: 29. Elektronische Sprachsignalverarbeitung 2018, Ulm, 7. - 10. März; Literaturverzeichnis: Seite 222-223]
Acoustic detection of consecutive stages of spoken interaction based on speaker-group specific features
Böck, Ronald; Egorow, Olga; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2018: Tagungsband der 29. Konferenz, Ulm, 7.-9. März 2018/ Konferenz "Elektronische Sprachsignalverarbeitung" - Dresden: TUDpress, 2018; Berton, André . - 2018, S. 247-254[Konferenz: 29. Elektronische Sprachsignalverarbeitung 2018, Ulm, 7. - 10. März; Literaturverzeichnis: Seite 252-254]
Peer-reviewed journal article
Using a PCA-based dataset similarity measure to improve cross-corpus emotion recogniton
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Computer speech and language - London: Academic Press, 1986 . - 2018, insges. 31 S.
An experimental paradigm for inducing emotions in a real world driving scenario evidence from self-report, annotation of speech data and peripheral physiology
Requardt, Alicia Flores; Wilbrink, Marc; Siegert, Ingo; Jipp, Meike; Wendemuth, Andreas; Ihme, Klas
In: Kognitive Systeme - Duisburg : DuEPublico, Duisburg-Essen Publication Online, Universität Duisburg-Essen . - 2018, Heft 1, insges. 12 S.
Dissertation
Automatic facial analysis methods - facial point localization, head pose estimation, and facial expression recognition
Saeed, Anwar Maresh Qahtan; Al-Hamadi, Ayoub; Wendemuth, Andreas
In: Magdeburg, 2018, xxx, 192 Seiten, Illustrationen, Tabellen, Diagramme[Literaturverzeichnis: Seite 169-188]
Spline-Methoden für die modellbasierte 3D-Oberflächeninspektion
Enzberg, Sebastian; Hamadi, Ayoub; Wendemuth, Andreas
In: Magdeburg, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Elektrotechnik und Informationstechnik 2018, 155 Seiten [Literaturverzeichnis: Seite 145-155][Literaturverzeichnis: Seite 145-155]
2017
Book chapter
Audio compression and its impact on emotion recognition in affective computing
Lotz, Alicia Flores; Siegert, Ingo; Maruschke, Michael; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2017: Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 / Jürgen Trouvain ; Ingmar Steiner und Bern Möbius (Hrsg.): Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 - Dresden: TUDpress Verlag der Wissenschaften GmbH, 2017 . - 2017, S. 1-8[Kongress: 28. Konferenz Elektronische Sprachsignalverarbeitung, Saarbrücken, 15. - 17. März, 2017]
Towards a sensor failure-dependent performance adaptation using the validity concept
Höbel, Juliane; Jäger, Georg; Zug, Sebastian; Wendemuth, Andreas
In: Computer Safety, Reliability, and Security - Cham : Springer ; Schoitsch, Erwin . - 2017, S. 270-286 - ( Lecture Notes in Computer Science; volume 10488) [Konferenz: 36th International Conference, SAFECOMP 2017, Trento, Italy, September 13-15, 2017]
ikannotate2 - a tool supporting annotation of emotions in audio-visual data
Siegert, Ingo; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2017: Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 / Jürgen Trouvain ; Ingmar Steiner und Bern Möbius (Hrsg.): Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 - Dresden: TUDpress Verlag der Wissenschaften GmbH, 2017 . - 2017, S. 17-24[Kongress: 28. Konferenz Elektronische Sprachsignalverarbeitung, Saarbrücken, 15. - 17. März, 2017]
Accelerating manual annotation of filled pauses by automatic pre-selection
Egorow, Olga; Lotz, Alicia Flores; Siegert, Ingo; Böck, Ronald; Krüger, Julia; Wendemuth, Andreas
In: 2017 International Conference on Companion Technology (ICCT): 11-13 Sept. 2017/ International Conference on Companion Technology - [Piscataway, NJ]: IEEE, 2017; International Conference on Companion Technology (2.:2017) . - 2017, insges. 6 S.[Konferenz: 2017 International Conference on Companion Technology (ICCT), Ulm, Germany, 11.-13. September 2017]
An introduction to companion-technology
Biundo, Susanne; Wendemuth, Andreas
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 1-15
Modeling aspects in human-computer interaction - adaptivity, user characteristics and evaluation
Gossen, Tatiana; Siegert, Ingo; Nürnberger, Andreas; Hartmann, Kim; Kotzyba, Michael; Wendemuth, Andreas
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 57-58
Multi-modal information processing in companion-systems - a ticket purchase system
Siegert, Ingo; Schüssel, Felix; Schmidt, Miriam; Reuter, Stephan; Meudt, Sascha; Layher, Georg; Krell, Gerald; Hörnle, Thilo; Handrich, Sebastian; Al-Hamadi, Ayoub; Dietmayer, Klaus; Neumann, Heiko; Palm, Günther; Schwenker, Friedhelm; Wendemuth, Andreas
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 493-500
Comparative study on normalisation in emotion recognition from speech
Böck, Ronald; Egorow, Olga; Siegert, Ingo; Wendemuth, Andreas
In: Intelligent human computer interaction / IHCI , 2017 - Cham : Springer ; Horain, Patrick, S. 189-201 - (Lecture Notes in Computer Science; 10688)
The last minute corpus as a research resource - from signal processing to behavioral analyses in user-companion interactions
Rösner, Dietmar; Frommer, Jörg; Wendemuth, Andreas; Bauer, Thomas; Günther, Stephan; Haase, Matthias; Siegert, Ingo
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 277-299
Multimodal affect recognition in the context of human-computer interaction for companion-systems
Schwenker, Friedhelm; Böck, Ronald; Schels, Martin; Meudt, Sascha; Siegert, Ingo; Glodek, Michael; Kächele, Markus; Schmidt-Wack, Miriam; Thiam, Patrick; Wendemuth, Andreas; Krell, Gerald
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 387-408
Emotion recognition from speech
Wendemuth, Andreas; Vlasenko, Bogdan; Siegert, Ingo; Böck, Ronald; Schwenker, Friedhelm; Palm, Günther
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 409-428
Speaker-group specific acoustic differences in consecutive stages of spoken interaction
Böck, Ronald; Egorow, Olga; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2017: Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 / Jürgen Trouvain ; Ingmar Steiner und Bern Möbius (Hrsg.): Tagungsband der 28. Konferenz Saarbrücken, 15. - 17. März 2017 - Dresden: TUDpress Verlag der Wissenschaften GmbH, 2017; Trouvain, Jürgen . - 2017, S. 211-218[Kongress: 28. Konferenz Elektronische Sprachsignalverarbeitung, Saarbrücken, 15. - 17. März, 2017]
Emotional features for speech overlaps classification
Egorow, Olga; Wendemuth, Andreas
In: INTERSPEECH 2017: 20-24 August 2017, Stockholm - International Speech and Communication Association, 2017; Lacerda, Francisco . - 2017, S. 2356-2360[Session: Social signals, styles, and interaction; Kongress: INTERSPEECH 2017, Stockholm, 20-14 August 2017]
Improving speech-based emotion recognition by using psychoacoustic modeling and analysis-by-synthesis
Siegert, Ingo; Lotz, Alicia Flores; Egorow, Olga; Wendemuth, Andreas
In: Speech and Computer: 19th International Conference, SPECOM 2017, Hatfield, UK, September 12-16, 2017, Proceedings - Cham: Springer, 2017; Potapova, Rodmonga . - 2017, S. 445-455 - (Lecture Notes in Computer Science; 10458)[Konferenz: 19th International Conference Speech and Computer, SPECOM 2017, Hatfield, UK, September 12-16, 2017]
Companion-systems - a reference architecture
Hörnle, Thilo; Tornow, Michael; Honold, Frank; Schwegler, Reinhard; Heinemann, Ralph; Biundo, Susanne; Wendemuth, Andreas
In: Companion technology - Cham : Springer ; Biundo-Stephan, Susanne *1955-* . - 2017, S. 449-469
Recognition of emotional speech with convolutional neural networks by means of spectral estimates
Weißkirchen, Norman; Böck, Ronald; Wendemuth, Andreas
In: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACII) ; Part 2 - IEEE, 2017; Part 2 . - 2017, S. 50-55[Konferenz: 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACII, San Antonio, Texas, 23. - 26.10.2017]
Peer-reviewed journal article
Prediction of user satisfaction in naturalistic human-computer interaction
Egorow, Olga; Siegert, Ingo; Wendemuth, Andreas
In: Kognitive Systeme - Duisburg: DuEPublico, Duisburg-Essen Publication Online, Universität Duisburg-Essen, 2013 . - 2017, 1, insges. 9 S.
Editor
Companion technology - a paradigm shift in human-technology interaction
Biundo-Stephan, Susanne; Wendemuth, Andreas
In: Cham: Springer, 2017, 1 Online-Ressource - (Cognitive technologies), ISBN: 978-3-319-43665-4
Companion technology - a paradigm shift in human-technology interaction
Biundo-Stephan, Susanne; Wendemuth, Andreas
In: Cham: Springer, 2017, 1 Online-Ressource - (Cognitive technologies), ISBN: 978-3-319-43665-4
2016
Book chapter
Discourse particles in human-human and human-computer interaction - Analysis and evaluation
Siegert, Ingo; Krüger, Julia; Haase, Matthias; Lotz, Alicia Flores; Günther, Stephan; Frommer, Jörg; Rösner, Dietmar; Wendemuth, Andreas
In: Human-Computer Interaction. Theory, Design, Development and Practice - Cham : Springer International Publishing ; Kurosu, Masaaki . - 2016, S. 105-117
Combined linear and nonlinear residual echo suppression using a deficient distortion model - a proof of concept
Schalk-Schupp, Ingo; Faubel, Friedrich; Buck, Markus; Wendemuth, Andreas
In: Speech communication / ITG-Fachtagung Sprachkommunikation , 2016 - Berlin : VDE Verlag, S. 312-316
Tendencies regarding the effect of emotional intensity in inter corpus phoneme-level speech emotion modelling
Vlasenko, Bogdan; Schuller, Björn; Wendemuth, Andreas
In: 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) / IEEE Image, Video, and Multidimensional Signal Processing Workshop , 2016 - Piscataway, NJ : IEEE ; IEEE Image, Video, and Multidimensional Signal Processing Workshop (12.:2016), insges. 6 S.
Measuring the impact of audio compression on the spectral quality of speech data
Siegert, Ingo; Lotz, Alicia Flores; Doung, Linh Linda; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2016 / Konferenz "Elektronische Sprachsignalverarbeitung" , 2016 - Dresden : TUDpress, S. 229-236 - (Studientexte zur Sprachkommunikation; Band 81)
Multimodale, dialogische Interaktion in der Industrie - auf dem Weg zur Industrie 5.0
Böck, Ronald; Wendemuth, Andreas
In: 3D SENSATION - transdisziplinäre Perspektiven: innteract conference - Chemnitz: Verlag aw&l Wissenschaft und Praxis, 2016 . - 2016, S. 392-401[Kongress: innteract conference 2016, Chemnitz, 23. - 24. Juni, 2016]
Modellierung von Verhaltens- und Handlungsintentionsverläufen aus multimodalen 3D-Daten
Egorow, Olga; Wendemuth, Andreas
In: 3D SENSATION - transdisziplinäre Perspektiven: innteract conference - Chemnitz: Verlag aw&l Wissenschaft und Praxis, 2016 . - 2016, S. 88-89[Kongress: Innteract conference 2016, Chemnitz, 23. - 24. Juni, 2016]
Detection of challenging dialogue stages using acoustic signals and biosignals
Egorow, Olga; Wendemuth, Andreas
In: WSCG 2016: 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2016, Plzen, Czech Republic, May 30 - June 3, 2016 ; short paper proceedings - Plzen: Vaclav Skala - Union Agency, 2016; Skala, Vaclav . - 2016, S. 137-143[Konferenz: 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2016, Plzen, Czech Republic, May 30 - June 3, 2016]
Multimodal information processing - the ticket purchase : a demonstration scenario of the SFB/TRR-62
Siegert, Ingo; Reuter, Stephan; Schüssel, Felix; Layer, Georg; Hörnle, Thilo; Meudt, Sascha; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2016: Tagungsband der 27. Konferenz, Leipzig, 2.-4. März 2016 / Oliver Jokisch (Hrsg.) ; Tagungsorganisation: Hochschule für Telekommunikation Leipzig, Institut für Kommunikationstechnik, Prof. Dr.-Ing. Oliver Jokisch: Tagungsband der 27. Konferenz, Leipzig, 2.-4. März 2016/ Konferenz "Elektronische Sprachsignalverarbeitung" - Dresden: TUDpress, 2016; Jokisch, Oliver . - 2016, S. 111-118 - (Studientexte zur Sprachkommunikation; Band 81)[Kongress: 27. Konferenz Elektronische Sprachsignalverarbeitung 2016: Tagungsband der 27. Konferenz, Leipzig, 2.-4. März 2016 / Oliver Jokisch (Hrsg.) ; Tagungsorganisation: Hochschule für Telekommunikation Leipzig, Institut für Kommunikationstechnik, Prof. Dr.-Ing. Oliver Jokisch, Leipzig, 2. - 4. März 2016]
Akustische Marker für eine verbesserte Situations- und Intentionserkennung von technischen Assistenzsystemen
Siegert, Ingo; Lotz, Alicia Flores; Egorow, Olga; Böck, Ronald; Schega, Lutz; Tornow, Michael; Thiers, Angelina; Wendemuth, Andreas
In: Technische Unterstützungssysteme, die die Menschen wirklich wollen: Zweite Transdisziplinäre Konferenz : Hamburg 2016 - Hamburg: Laboratorium Fertigungstechnik, smartASSIST, Helmut Schmidt Universität$, S. 465-474[Kongress: 2. Transdisziplinäre Konferenz "Technische Unterstützungssysteme, die die Menschen wirklich wollen", Hamburg, 2016]
Kennzeichnung von Nutzerprofilen zur Interaktionssteuerung beim Gehen
Thiers, Angelina; Hamacher, Dennis; Tornow, Michael; Heinemann, Ralph; Siegert, Ingo; Wendemuth, Andreas; Schega, Lutz
In: Technische Unterstützungssysteme, die die Menschen wirklich wollen / Transdisziplinäre Konferenz Technische Unterstützungssysteme, die die Menschen Wirklich Wollen , 2016 - Hamburg : Laboratorium Fertigungstechnik, smartASSIST, Helmut Schmidt Universität, S. 475-484
Developing recording and synchronous handling of ten modalities in affective human machine interactions
Wendemuth, Andreas
In: Proceedings of the 2nd workshop on Emotion Representations and Modelling for Companion Systems: November 16, 2016, Tokyo, Japan - New York, NY: ACM, S. 13-14[Kongress: 2nd Workshop on Emotion Representations and Modelling for Companion Systems, Tokyo, Japan, 16. November, 2016]
Approximation of a nonlinear distortion function for combined linear and nonlinear residual echo suppression
Schalk-Schupp, Ingo; Faubel, Friedrich; Buck, Markus; Wendemuth, Andreas
In: 2016 International Workshop on Acoustic Signal Enhancement (IWAENC): September 13-16, 2016, Xi'an, China - [Piscataway, NJ]: IEEE[Kongress: 2016 International Workshop on Acoustic Signal Enhancement (IWAENC), Xian, China, 13-16 September, 2016]
Annotators agreement and spontaneous emotion classification performance
Vlasenko, Bogdan; Wendemuth, Andreas
In: Speech beyond speech towards a better understanding of the most important biosignal / International Speech Communication Association , 2015 - Red Hook, NY : Curran Associates, Inc. . - 2016, S. 1546-1550
Classification of functional-meanings of non-isolated discourse particles in human-human-interaction
Lotz, Alicia Flores; Siegert, Ingo; Wendemuth, Andreas
In: Human-Computer Interaction. Theory, Design, Development and Practice - Cham : Springer International Publishing ; Kurosu, Masaaki . - 2016, S. 53-64 - (Lecture Notes in Computer Science; 9731)
Emotion intelligibility within codec-compressed and reduced bandwidth speech
Siegert, Ingo; Lotz, Alicia Flores; Maruschke, Michael; Jokisch, Oliver; Wendemuth, Andreas
In: Speech communication / ITG-Fachtagung Sprachkommunikation , 2016 - Berlin : VDE Verlag, S. 215-219
Peer-reviewed journal article
Counting votes in coupled decisions - an efficient method for counting votes in coupled decisions with multiple inequality restrictions
Wendemuth, Andreas; Simonelli, Italo
In: Theory and decision - Dordrecht [u.a.] : Springer Science + Business Media B.V., Bd. 81 (2016), S. 213-253
Comparison of different modeling techniques for robust prototype matching of speech pitch-contours
Lotz, Alicia Flores; Siegert, Ingo; Wendemuth, Andreas
In: Kognitive Systeme - Duisburg: DuEPublico, 1, insges. 10 S., 2016
Article in conference proceedings
Integrated health and fitness (iGF)-corpus - ten-modal highly synchronized subject-dispositional and emotional human machine interactions
Tornow, Michael; Krippl, Martin; Bade, Svea; Thiers, Angelina; Siegert, Ingo; Handrich, Sebastian; Krüger, Julia; Schega, Lutz; Wendemuth, Andreas
In: Kongress: MMC 2016, Portorož, 2016.05.24, Multimodal Corpora: Computer vision and language processing (MMC 2016) - ELRA, S. 21-24
2015
Book chapter
NaLMC - a database on non-acted and acted emotional sequences in HCI
Hartmann, Kim; Krüger, Julia; Frommer, Jörg; Wendemuth, Andreas
In: Proceedings of the 2015 ACM International Conference on Multimodal Interaction: November 9 - 13, 2015, Seattle, Washington / sponsored by: ACM SIGCHI: November 9 - 13, 2015, Seattle, Washington/ ICMI - New York, NY: ACM, 2015 . - 2015, S. 199-202
Automatic differentiation of form-function-relations of the discourse particle "hm" in a naturalistic human-computer interaction
Lotz, Alicia Flores; Siegert, Ingo; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2015: Tagungsband der 26. Konferenz, Eichstätt, 25. - 27. März 2015 / [26. Konferenz "Elektronische Sprachsignalverarbeitung"]. Günther Wirsching (Hrsg.). [Mitw. Förderverein Elektronische Sprachsignalverarbeitung e.V. Tagungsort Katholische Universität Eichstätt-Ingolstadt. Tagungsorganisation Katholische Universität Eichstätt-Ingolstadt, Lehrstuhl für Mathematik-Statistik]: Tagungsband der 26. Konferenz, Eichstätt, 25. - 27. März 2015 - Dresden: TUDpress, 2015 . - 2015, S. 172-179 - (Studientexte zur Sprachkommunikation; 78)Kongress: Konferenz "Elektronische Sprachsignalverarbeitung 26 (Eichstätt : 2015)
Companion-Systeme - soziale Agenten mit kognitiven Fähigkeiten
Wendemuth, Andreas
In: Die Technisierung des Menschlichen und die Humanisierung der Maschine: interdisziplinäre Beiträge zur Interdependenz von Mensch und Technik - Halle (Saale): Mitteldeutscher Verlag, 2015 . - 2015, S. 75-100
Cross-corpus acoustic emotion recognition - variances and strategies (extended abstract)
Schuller, Björn; Vlasenko, Bogdan; Eyben, Florian; Wollmer, Martin; Stuhlsatz, André; Wendemuth, Andreas; Rigoll, Gerhard
In: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII): 21 - 24 Sept. 2015, Xi'an - Piscataway, NJ: IEEE, 2015 . - 2015, S. 470 - 476[Kongress: International Conference on Affective Computing and Intelligent Interaction (ACII), 21 - 24 Sept. 2015, Xi'an]
Overlapping speech, utterance duration and affective content in HHI and HCI - an comparison
Siegert, Ingo; Böck, Ronald; Vlasenko, Bogdan; Ohnemus, Kerstin; Wendemuth, Andreas
In: CogInfoCom 2015 , 2015 - [Piscataway, NJ] : IEEE ; CogInfoCom (6.:2015), S. 83-88
Ein Datenset zur Untersuchung emotionaler Sprache in Kundenbindungsdialogen
Siegert, Ingo; Philippou-Hübner, David; Tornow, Michael; Heinemann, Ralph; Wendemuth, Andreas; Ohnemus, Kerstin; Fischer, Sarah; Schreiber, Gerald
In: Elektronische Sprachsignalverarbeitung 2015: Tagungsband der 26. Konferenz, Eichstätt, 25. - 27. März 2015 - Dresden: TUDpress, S. 180-187 - (Studientexte zur Sprachkommunikation; 78)Kongress: Konferenz "Elektronische Sprachsignalverarbeitung 26 (Eichstätt : 2015)
Peer-reviewed journal article
Probabilistic breadth as an evaluation measure of gaussian mixture models used for acoustic emotion states
Böck, Ronald; Siegert, Ingo; Wendemuth, Andreas
In: Kognitive Systeme - Duisburg: DuEPublico, Duisburg-Essen Publication Online, Universität Duisburg-Essen, 2013 . - 2015, 2, insges. 8 S.
Exploratory voice-controlled search for young users - Challenges & Potential Benefits
Kotzyba, Michael; Siegert, Ingo; Gossen, Tatiana; Wendemuth, Andreas; Nürnberger, Andreas
In: Kognitive Systeme - Duisburg : DuEPublico, Duisburg-Essen Publication Online, Universität Duisburg-Essen . - 2015, Heft 1, insges. 10 S.
Companion-technology for cognitive technical systems
Wendemuth, Andreas; Biundo, Susanne
In: Künstliche Intelligenz: KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI - Berlin: Springer, 2010 . - 2015, insges. 5 S.
Dissertation
Emotional and user-specific cues for improved analysis of naturalistic interactions
Siegert, Ingo; Wendemuth, Andreas; Diedrich, Christian
In: Magdeburg, Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2015, XIX, 266 S.
Article in conference proceedings
Functional analysis of pitch contours for disposition recognition from speech
Prylipko, Dmytro; Böck, Ronald; Wendemuth, Andreas
In: 4. Interdisziplinärer Workshop Kognitive Systeme 2015: Mensch, Teams, Systeme und Automaten: proceedings - Bielefeld, 2015 . - 2015, insges. 6 S.Kongress: Interdisziplinärer Workshop Kognitive Systeme 4 (Bielefeld : 2015.03.23-25)
Probabilistic breadth used in evaluation of resulting gaussian mixture models
Böck, Ronald; Siegert, Ingo; Wendemuth, Andreas
In: 4. Interdisziplinärer Workshop Kognitive Systeme 2015: Mensch, Teams, Systeme und Automaten: proceedings - Bielefeld, 2015 . - 2015, insges. 8 S.Kongress: Interdisziplinärer Workshop Kognitive Systeme 4 (Bielefeld : 2015.03.23-25)
Exploring dataset similarities using PCA-based feature selection
Siegert, Ingo; Böck, Ronald; Vlasenko, Bogdan; Wendemuth, Andreas
In: 2015 International Conference on Affective Computing and Intelligent Interaction (ACII): 21 - 24 Sept. 2015, Xi'an - Piscataway, NJ: IEEE, 2015 . - 2015, S. 387-393
2014
Book chapter
Location of an emotionally neutral region in valence-arousal space - two-class vs. three-class cross corpora emotion recognition evaluations
Vlasenko, B.; Wendemuth, Andreas
In: IEEE International Conference on Multimedia and Expo workshops (ICMEW), 2014: 14 - 18 July 2014, Chengdu, China - Piscataway, NJ: IEEE, 2014 . - 2014, insges. 6 S.
Discourse particles and user characteristics in naturalistic human-computer interaction
Siegert, Ingo; Haase, Matthias; Prylipko, Dmytro; Wendemuth, Andreas
In: Human-Computer Interaction. Advanced Interaction Modalities and Techniques / Kurosu , Masaaki - Cham [u.a.] : Springer ; Kurosu, Masaaki . - 2014, S. 492-501 - (Lecture notes in computer science; 8511) Kongress: HCI International 16 Heraklion, Crete 2014.06.22-27
Investigating the form-function-relation of the discourse particle “hm” in a naturalistic human-computer interaction
Siegert, Ingo; Prylipko, Dmytro; Hartmann, Kim; Böck, Ronald; Wendemuth, Andreas
In: Recent Advances of Neural Network Models and Applications / Bassis , Simone - Cham : Springer International Publishing ; Bassis, Simone . - 2014, S. 387-394 - (Smart Innovation, Systems and Technologies; 26)
Peer-reviewed journal article
Modeling phonetic pattern variability in favor of the creation of robust emotion classifiers for real-life applications
Vlasenko, Bogdan; Prylipko, Dmytro; Böck, Ronald; Wendemuth, Andreas
In: Computer speech and language - London: Academic Press, 1986, Bd. 28.2014, 2, S. 483-500
Investigation of speaker group-dependent modelling for recognition of affective states from speech
Siegert, Ingo; Philippou-Hübner, David; Hartmann, Kim; Böck, Ronald; Wendemuth, Andreas
In: Cognitive Computation - New York, NY: Springer, 2009, Bd. 6.2014, 4, S. 892-913
Analysis of significant dialog events in realistic human-computer interaction
Prylipko, Dmytro; Rösner, Dietmar; Siegert, Ingo; Günther, Stephan; Friesen, Rafael; Haase, Matthias; Vlasenko, Bogdan; Wendemuth, Andreas
In: Journal on multimodal user interfaces - Berlin: Springer, 2007, Bd. 8.2014, 1, S. 75-86
Learning long-term dependencies in segmented-memory recurrent neural networks with backpropagation of error
Glüge, Stefan; Böck, Ronald; Palm, Günther; Wendemuth, Andreas
In: Neurocomputing: an international journal - Amsterdam: Elsevier, 1989, Bd. 141.2014, S. 54-64
Article in conference proceedings
Application of image processing methods to filled pauses detection from spontaneous speech
Prylipko, Dmytro; Egorow, O.; Siegert, Ingo; Wendemuth, Andreas
In: 15th annual conference of the International Speech Communication Association, INTERSPEECH: Singapore, 14 - 18 September 2014 - International Speech and Communication Association, S. 1816-1820Kongress: INTERSPEECH 15 (Singapore : 2014.09.14-18)
Non-peer-reviewed journal article
Companion-Systeme - interaktive, kognitive Informationstechnik
Wendemuth, Andreas
In: Mitteldeutsche Mitteilungen - Forum technisch-wissenschaftlicher Vereine und Verbände: Informationen aus Wirtschaft, Wissenschaft, Gesellschaft : Forum der technisch-wissenschaftlichen Vereine und Verbände Sachsen-Anhalts - Magdeburg: VDI, Landesverband Sachsen-Anhalt, 1999, Bd. 23.2014, 3, S. 12-13
2013
Book chapter
Emotion detection in HCI - from speech features to emotion space?
Hartmann, Kim; Siegert, Ingo; Philippou-Hübner, David; Wendemuth, Andreas
In: 7th IFAC Conference on Manufacturing Modelling, Management, and Control, 2013. - IFAC, S. 288-295Kongress: IFAC Conference on Manufacturing Modelling, Management, and Control; 7 (Saint Petersburg) : 2013.06.19-21
Fusion of fragmentary classifier decisions for affective state recognition
Krell, Gerald; Glodek, Michael; Panning, Axel; Siegert, Ingo; Michaelis, Bernd; Wendemuth, Andreas; Schwenker, Friedhelm
In: Multimodal pattern recognition of social signals in human-computer-interaction : first IAPR TC3 workshop, MPRSS 2012, Tsukuba, Japan, November 11, 2012 ; revised selected papers. - Berlin [u.a.] : Springer, S. 116-130, 2013 - (Lecture notes in computer science; 7742)Kongress: MPRSS; 1 (Tsukuba) : 2012.11.11
Auto-encoder pre-training of segmented-memory recurrent neural networks
Glüge, Stefan; Böck, Ronald; Wendemuth, Andreas
In: Proceedings: Bruges, Belgium, April 24 - 25 - 26, 2013 / [organised in collaboration with: UCL (Université Catholique de Louvain, Louvain-la-Neuve); KULeuven (Katholiek Universiteit Leuven). Ed.: Michel Verleysen]: Bruges, Belgium, April 24 - 25 - 26, 2013 - Louvain-la-Neuve: Ciaco, 2013 . - 2013, S. 29Kongress: ESANN 21 (Bruges : 2013.04.24-26)
Characterization of Lamb wave attenuation mechanisms
Schmidt, Daniel; Sadri, Hossein; Szewieczek, Artur; Sinapius, Michael; Wierach, Peter; Siegert, Ingo; Wendemuth, Andreas
In: Health monitoring of structural and biological systems 2013 : 11 - 14 March 2013, San Diego, California, United States ; [part of SPIE smart structures/NDE]. - Bellingham, Wash. : SPIE - (Proceedings of SPIE; 8695)Kongress: Conference on Health Monitoring of Structural and Biological Systems; (San Diego, Calif.) : 2013.03.11-14
Audio-based pre-classification for semi-automatic facial expression coding
Böck, Ronald; Limbrecht-Ecklundt, Kerstin; Siegert, Ingo; Walter, Steffen; Wendemuth, Andreas
In: Human-computer interaction ; Pt. 5:Towards intelligent and implicit interaction - Berlin [u.a.]: Springer, 2013 . - 2013, S. 301-309 - (Lecture notes in computer science; 8008)Kongress: HCI International 15 (Las Vegas, Nev. : 2013.07.21-26)
The influence of context knowledge for multi-modal affective annotation
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Human-computer interaction ; Pt. 5:Towards intelligent and implicit interaction - Berlin [u.a.]: Springer, 2013 . - 2013, S. 381-390 - (Lecture notes in computer science; 8008)Kongress: HCI International 15 (Las Vegas, Nev. : 2013.07.21-26)
Dempster-shafer theory with smoothness
Böck, Ronald; Glüge, Stefan; Wendemuth, Andreas
In: Integrated Uncertainty in Knowledge Modelling and Decision Making / Qin , Zengchang - Berlin, Heidelberg : Springer ; Qin, Zengchang . - 2013, S. 13-22 - (Lecture notes in computer science; 8032) Kongress: IUKM Beijing 2013.07.12-14
Using speaker group dependent modelling to improve fusion of fragmentary classifier decisions
Siegert, Ingo; Glodek, Michael; Panning, Axel; Krell, Gerald; Schwenker, Friedhelm; Al-Hamadi, Ayoub; Wendemuth, Andreas
In: Proceedings of the 2013 IEEE International Conference on Cybernetics (CYBCONF 2013) : Lausanne, Switzerland, 13-15 June, 2013. - IEEE, S. 132-137Kongress: CYBCONF; (Lausanne, Switzerland) : 2013.06.13-15
Annotation and classification of changes of involvement in group conversation
Böck, Ronald; Glüge, Stefan; Siegert, Ingo; Wendemuth, Andreas
In: Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII), 2013 - Piscataway, NJ : IEEE, S. 803-808
Human behaviour in HCI - complex emotion detection through sparse speech features
Siegert, Ingo; Hartmann, Kim; Philippou-Hübner, David; Wendemuth, Andreas
In: Human Behavior Understanding / Salah , Albert Ali - Cham [u.a.] : Springer ; Salah, Albert Ali . - 2013, S. 246-257 - (Lecture notes in computer science; 8212) Kongress: HBU 4 Barcelona 2013.10.22
Solving number series with simple recurrent networks
Glüge, Stefan; Wendemuth, Andreas
In: Natural and Artificial Models in Computation and Biology / Ferrández Vicente , José Manuel - Berlin, Heidelberg : Springer ; Ferrández Vicente, José Manuel . - 2013, S. 412-420 - (Lecture notes in computer science; volume 7930)
Determining the smallest emotional unit for level of arousal classification
Vlasenko, Bogdan; Wendemuth, Andreas
In: Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII), 2013 - Piscataway, NJ : IEEE, S. 734-739
Peer-reviewed journal article
Modelling of emotional development within human-computer-interaction
Siegert, Ingo; Hartmann, Kim; Glüge, Stefan; Wendemuth, Andreas
In: Kognitive Systeme. - Duisburg : DuEPublico, 1, insges. 8 S., 2013
Inter-rater reliability for emotion annotation in human-computer interaction - comparison and methodological improvements
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Journal on multimodal user interfaces - Berlin: Springer, 2007 . - 2013
Dissertation
Implicit sequence learning in recurrent neural networks
Glüge, Stefan; Wendemuth, Andreas; Al-Hamadi, Ayoub
In: Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013, VIII, 132 S., graph. Darst.
Multimodal automatic user disposition recognition in human-machine interaction
Böck, Ronald; Wendemuth, Andreas; Diedrich, Christian
In: Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013: Magdeburg, XVII, 206 S., graph. Darst.
2012
Abstract
Emotion detection by event evaluation using fuzzy sets as appraisal variables
Kotzyba, Michael; Deml, Barbara; Neumann, Hendrik; Glüge, Stefan; Hartmann, Kim; Siegert, Ingo; Wendemuth, Andreas; Traue, Harald; Walter, Steffen
In: Proceedings of ICCM 2012 : 11th International Conference on Cognitive Modeling. - Berlin : Universitätsverl. der TU Berlin, S. 123-124
Book chapter
Fine-tuning HMMS for nonverbal vocalizations in spontaneous speech - a multicorpus perspective
Prylipko, Dmytro; Schuller, Björn; Wendemuth, Andreas
In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012: 25 - 30 March 2012, Kyoto, Japan ; proceedings - Piscataway, NJ: IEEE, 2012 . - 2012, S. 4625-4628Kongress: TSD 15 (Brno, Czech Republic : 2012.09.03-07)
Language modeling of nonverbal vocalizations in spontaneous speech
Prylipko, Dmytro; Vlasenko, Bogdan; Stolcke, Andreas; Wendemuth, Andreas
In: Text, Speech and Dialogue / Sojka , Petr - Berlin, Heidelberg : Springer ; Sojka, Petr . - 2012, S. 488-495 - (Lecture notes in computer science; 7499) Kongress: TSD 15 Brno, Czech Republic 2012.09.03-07
Multimodal affect recognition in spontaneous HCI environment
Panning, Axel; Siegert, Ingo; Al-Hamadi, Ayoub; Wendemuth, Andreas; Rösner, Dietmar; Frommer, Jörg; Krell, Gerald; Michaelis, Bernd
In: 2012 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC 2012) : Hong Kong, China, 12-15 August 2012 ; proceedings. - Piscataway, NJ : IEEE, insges. 6 S.Kongress: ICSPCC; (Hong Kong) : 2012.08.12-15
Towards emotion and affect detection in the multimodal LAST MINUTE corpus
Frommer, Jörg; Michaelis, Bernd; Rösner, Dietmar; Wendemuth, Andreas; Friesen, Rafael; Haase, Matthias; Kunze, Manuela; Andrich, Rico; Krüger, Julia; Panning, Axel; Siegert, Ingo
In: Proceedings of the 8th International Conference on Language Resources and Evaluation: May 23-25, 2012 / eds. Nicoletta Calzolari: May 23-25, 2012 - ELRA, 2012; Calzolari, Nicoletta . - 2012, S. 3064-3069Kongress: LREC 2010 8 (Istanbul, Turkey : 2012.05.23-25)
The Influence of Context Knowledge for Multimodal Annotation
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Joint proceedings of the IVA 2012 workshops - Santa Cruz, California, September 15, 2012 - Magdeburg: Univ. . - 2012, S. 25-31Kongress: IVA 12 (Santa Cruz, Calif. : 2012.09.12-15)
Describing human emotions through mathematical modelling
Hartmann, Kim; Siegert, Ingo; Glüge, Stefan; Wendemuth, Andreas; Kotzyba, Michael; Deml, Barbara
In: Preprints MATHMOD 2012 Vienna : abstract volume. - Vienna : ARGESIM, ARGE Simulation News, Vienna Univ. of Technology, insges. 6 S. - (ARGESIM report; 38)Kongress: MATHMOD; 7 (Vienna) : 2012.02.15-17
Extension of backpropagation through time for segmented-memory recurrent neural networks
Glüge, Stefan; Böck, Ronald; Wendemuth, Andreas
In: Proceedings of the 4th International Joint Conference on Computational Intelligence: Barcelona, Spain, 5 - 7 October 2012 / sponsored by INSTICC, Institute for Systems and Technologies of Information, Control and Communication. [Ed. by Agostinho Rosa, ...] - [S.l.]: SciTePress; Rosa, Agostinho . - 2012, S. 451-456Kongress: IJCCI 4 (Barcelona, Spain : 2012.10.05-07)
Intraindividual and interindividual multimodal emotion analyses in human-machine-interaction
Böck, Ronald; Glüge, Stefan; Wendemuth, Andreas; Limbrecht, Kerstin; Walter, Steffen; Hrabal, David; Traue, Harald C.
In: 2012 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA 2012): New Orleans, Louisiana, USA, 6 - 8 March 2012 - Piscataway, NJ: IEEE, 2012 . - 2012, S. 59-64Kongress: CogSIMA (New Orleans, La. : 2012.03.06-08)
Investigation of hierarchical classification for simultaneous gender and age recognition
Siegert, Ingo; Böck, Ronald; Philippou-Hübner, David; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2012 - Dresden: TUDpress Verl. der Wiss.; Wolff, Matthias . - 2012, S. 58 - (Studientexte zur Sprachkommunikation; 64)Kongress: Konferenz Elektronische Sprachsignalverarbeitung 23 (Cottbus : 2012.08.29-31)
Combining mimic and prosodic analyses for user disposition classification
Böck, Ronald; Limbrecht, Kerstin; Siegert, Ingo; Glüge, Stefan; Walter, Steffen; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2012 - Dresden: TUDpress Verl. der Wiss.; Wolff, Matthias . - 2012, S. 220 - (Studientexte zur Sprachkommunikation; 64)Kongress: Konferenz Elektronische Sprachsignalverarbeitung 23 (Cottbus : 2012.08.29-31)
Applying the speaking rate in a hierarchical classifier for emotion recognition from speech
Philippou-Hübner, David; Böck, Ronald; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung 2012 - Dresden: TUDpress Verl. der Wiss.; Wolff, Matthias . - 2012, S. 228 - (Studientexte zur Sprachkommunikation; 64)Kongress: Konferenz Elektronische Sprachsignalverarbeitung 23 (Cottbus : 2012.08.29-31)
The performance of the speaking rate parameter in emotion recognition from speech
Philippou-Hübner, David; Vlasenko, Bogdan; Böck, Ronald; Wendemuth, Andreas
In: 2012 IEEE International Conference on Multimedia and Expo - Piscataway: IEEE . - 2012, S. 248-253Kongress: ICME (Melbourne, Australia : 2012.07.09-13)
Modeling users' mood state to improve human-machine-interaction
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Cognitive behavioural systems - Berlin [u.a.]: Springer; Esposito, Anna . - 2012, S. 273-279 - (Lecture Notes in Computer Science; 7403)Kongress: COST Dresden : 2011.02.21-26
A companion technology for cognitive technical systems
Wendemuth, Andreas; Biundo, Susanne
In: Cognitive behavioural systems - Berlin [u.a.]: Springer; Esposito, Anna . - 2012, S. 89-103 - (Lecture Notes in Computer Science; 7403)
Peer-reviewed journal article
Majority decisions in overlapping committees and asymptotic size of dichotomies
Wendemuth, Andreas; Simonelli, Italo
In: SIAM journal on discrete mathematics/ Society for Industrial and Applied Mathematics - Philadelphia, Pa.: Soc., 1988, Bd. 26.2012, 4, S. 1537-1549
Article in conference proceedings
Towards robust spontaneous speech recognition with emotional speech adapted acoustic models
Vlasenko, Bogdan; Prylipko, Dmytro; Wendemuth, Andreas
In: KI 2012: Poster and Demo Track: 35th German Conference on Artifical Intelligence, Saarbrücken, Germany, September 24-27, 2012 - Saarbrücken, 2012 . - 2012, S. 103-107Kongress: KI 2012 (Saarbrücken : 2012.09.24-27)
2011
Abstract
Incorporation of a mood-model to improve user-disposition prediction from emotion recognition
Siegert, Ingo; Böck, Ronald; Wendemuth, Andreas
In: Program and abstracts of the COST 2102 Final Conference: held in conjunction with the 4th COST 2102 International Training School on Cognitive Behavioural Systems ; February 21 - 25, 2011, Dresden, Germany / Technische Universität Dresden, Institut für Akustik und Sprachkommunikation. [Ed. by Anna Esposito ...]: held in conjunction with the 4th COST 2102 International Training School on Cognitive Behavioural Systems ; February 21 - 25, 2011, Dresden, Germany - Dresden: Techn. Univ., Inst. für Akustik und Sprachkommunikation, 2011; Esposito, Anna . - 2011, S. 34[Kongress: COST 2102 Final Conference, Dresden, Germany, February 21 - 25, 2011]
Book chapter
Ikannotate - a tool for labelling, transcription, and annotation of emotionally coloured speech
Böck, Ronald; Siegert, Ingo; Haase, Matthias; Lange, Julia; Wendemuth, Andreas
In: Affective computing and intelligent interaction ; Pt. 1 - Heidelberg [u.a.]: Springer, 2011; Pt. 1 . - 2011, S. 25-34 - (Lecture notes in computer science; 6974)Kongress: ACII 4 (Memphis, TN : 2011.10.09-12)
Vowels formants analysis allows straightforward detection of high arousal emotions
Vlasenko, Bogdan; Philippou-Hübner, David; Prylipko, Dmytro; Böck, Ronald; Siegert, Ingo; Wendemuth, Andreas
In: 2011 IEEE International Conference on Multimedia and Expo: ICME 2011 ; electronic proceedings - Piscataway, NJ: IEEE, 2011; Chen, Irene, 2011, paper 631, insgesamt 6 S.Kongress: ICME (Barcelona, Spain : 2011.07.11-15)[Beitrag auf USB-Stick]
A processing tool for emotionally coloured speech
Böck, Ronald; Siegert, Ingo; Vlasenko, Bogdan; Wendemuth, Andreas; Haase, Matthias; Lange, Julia
In: 2011 IEEE International Conference on Multimedia and Expo: ICME 2011 ; electronic proceedings - Piscataway, NJ: IEEE, 2011; Chen, Irene, 2011, paper 895, insgesamt 1 S.Kongress: ICME (Barcelona, Spain : 2011.07.11-15)[Beitrag auf USB-Stick]
Appropriate emotional labelling of non-acted speech using basic emotions, geneva emotion wheel and self assessment manikins
Siegert, Ingo; Böck, Ronald; Philippou-Hübner, David; Vlasenko, Bogdan; Wendemuth, Andreas
In: 2011 IEEE International Conference on Multimedia and Expo: ICME 2011 ; electronic proceedings - Piscataway, NJ: IEEE, 2011; Chen, Irene, 2011, paper 419, insgesamt 6 S.Kongress: ICME (Barcelona, Spain : 2011.07.11-15)[Beitrag auf USB-Stick]
Multi-modal fusion with particle filter for speaker localization and tracking
Heuer, Michael; Hamadi, Ayoub; Michaelis, Bernd; Wendemuth, Andreas
In: 2011 International Conference on Multimedia Technology ; Vol. 7 - Piscataway, NJ: IEEE, 2011; Vol. 7 . - 2011, S. 6450-6453Kongress: ICMT (Hangzhou, China : 2011.07.26-28)
Dissertation
Emotion recognition within spoken dialog systems
Vlasenko, Bogdan; Wendemuth, Andreas; Rösner, Dietmar
In: Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2011, XXVII, 179 S.
Ökonomische Objektivierung von elektromechanischen Funktionsgeräuschen
Scheibner, Philipp; Wendemuth, Andreas
In: Berlin: Logos-Verl., 2012, Zugl.: Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik., Diss., 2011, X, 138 S., ISBN: 978-3-8325-3069-3
Article in conference proceedings
Segmented-memory recurrent neural networks versus Hidden Markov Models in emotion recognition from speech
Glüge, Stefan; Böck, Ronald; Wendemuth, Andreas
In: IC3K 2011: 3rd International Joint Conference on Knowledge, Knowledge Engineering and Knowledge Management, Paris, France, 26 - 29 October, 2011 - Paris, 2011 . - 2011, S. 308-315
Original article in peer-reviewed periodical-type series
Vowels formants analysis allows straightforward detection of high arousal acted and spontaneous emotions
Vlasenko, Bogdan; Prylipko, Dmytro; Philippou-Hübner, David; Wendemuth, Andreas
In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, (Interspeech 2010) : 26 - 30 September, 2010, Makuhari, Chiba, Japan. - ISCA, S. 1577-1580, 2011Kongress: Interspeech 2010; 11 (Makuhari, Chiba, Japan) : 2010.09.26-30
Zanzibar OpenIVR - an open-source framework for development of spoken dialog systems
Prylipko, Dmytro; Schnelle-Walka, Dirk; Lord, Spencer; Wendemuth, Andreas
In: Text, speech and dialogue : 14th international conference, TSD 2011, Pilsen, Czech Republic, September 1-5, 2011 ; proceedings. - Heidelberg [u.a.] : Springer, S. 372-379 - (Lecture notes in computer science; 6836)Kongress: TSD; 14 (Pilsen) : 2011.09.01-05
A Markov model of conditional associative learning in a cognitive behavioural scenario
Glüge, Stefan; Hamid, Oussama H.; Braun, Jochen; Wendemuth, Andreas
In: Foundations on natural and artificial computation - Heidelberg [u.a.]: Springer, S. 10-19, 2011 - (Lecture notes in computer science; 6686)Kongress: IWINAC 4 (La Palma : 2011.05.30-06.03
2010
Book chapter
Adaptive beamforming in speaker diarization
Grosser, Tobias; Elsafadi, Aoys; Hübner, David; Böck, Ronald; Wendemuth, Andreas
In: Proceedings - Berlin . - 2010, insges. 9 S.
Implicit sequence learning - a case study with a 4-2-4 encoder simple recurrent network
Glüge, Stefan; Böck, Ronald; Wendemuth, Andreas
In: IJCCI 2010 - Setúbal: SciTePress . - 2010, S. 279-288Kongress: ICNC 2010 (Valencia, Spain) ; 2010.10.24-26
Determining optimal signal features and parameters for HMM-based emotion classification
Böck, Ronald; Hübner, David; Wendemuth, Andreas
In: 15th IEEE Mediterranian Electromechanical Conference - IEEE . - 2010, S. 1586-1590Kongress: Melecon 2010 15 (Valletta, Malta : 2010.04.25-28)
Dissertation
Machine learning with Lipschitz classifiers
Stuhlsatz, André; Wendemuth, Andreas; Findeisen, Rolf
In: Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2010, VII, 200 S., graph. Darst.
Article in conference proceedings
Modeling affected user behavior during human-machine interaction
Vlasenko, Bogdan; Böck, Ronald; Wendemuth, Andreas
In: Proceedings of the 5th International Conference Speech prosody 2010 - Chicago . - 2010, insges. 4 S.Kongress: International Conference on Speech Prosody 5 (Chicago, Ill. : 2010.05.11-14)
Original article in peer-reviewed international journal
A simple recurrent network for implicit learning of temporal sequences
Glüge, Stefan; Hamid, Oussama H.; Wendemuth, Andreas
In: Cognitive Computation - New York, NY : Springer, Bd. 2 (2010), Heft 4, S. 265-271
Temporal context and conditional associative learning
Hamid, Oussama H.; Wendemuth, Andreas; Braun, Jochen
In: BMC neuroscience - London: BioMed Central, Bd. 11 (2010), insges. 15 S.
Cross-corpus acoustic emotion recognition - variances and strategies
Schuller, Björn; Vlasenko, Bogdan; Eyben, Florian; Wöllmer, Martin; Stuhlsatz, André; Wendemuth, Andreas; Rigoll, Gerhard
In: Institute of Electrical and Electronics Engineers : IEEE transactions on affective computing . - New York, NY : IEEE, Abstract
A simple recurrent network for implicit learning of temporal sequences
Glüge, Stefan; Hamid, Oussama H.; Wendemuth, Andreas
In: Cognitive computation - New York, N.Y.: Springer, 2009, Bd. 2.2010, 4, S. 265-271[From the issue entitled "Special Issue: Advances in Computational Intelligence and Applications - ISNN 2010"]
Temporal context and conditional associative learning
Hamid, O; Wendemuth, A; Braun, J
In: BMC Neuroscience
Original article in peer-reviewed national journal
Von kognitiven technischen Systemen zu Companion-Systemen
Biundo, Susanne; Wendemuth, Andreas
In: Künstliche Intelligenz . - Berlin : Springer, insges. 5 S.; Abstract
Original article in peer-reviewed periodical-type series
Determining optimal features for emotion recognition from speech by applying an evolutionary algorithm
Hübner, David; Vlasenko, Bogdan; Grosser, Tobias; Wendemuth, Andreas
In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, (Interspeech 2010) . - ISCA, S. 2358-2361Kongress: Interspeech 2010; 11 (Makuhari, Chiba, Japan) : 2010.09.26-30
2009
Book chapter
Sound quality evaluation of power seat adjusters
Scheibner, Philipp; Zeitler, Alfred; Wendemuth, Andreas
In: NAG DAGA <2009, Rotterdam> : Proceedings // NAG/DAGA 2009 . - [Berlin] : DEGA [u.a.], ISBN 978-3-9808659-6-8, S. 1547-1549Kongress: NAG/DAGA; (Rotterdam) : 2009.03.23-26
On the influences of feature extration in single emotion recognition in naive vs. acted speech
Böck, Ronald; Hübner, David; Wendemuth, Andreas
In: Tagungsband der 20. Konferenz, Dresden, 21. bis 23. September 2009 - Dresden: TUDpress; Hoffmann, Rüdiger . - 2009, S. 207-214 - (Studientexte zur Sprachkommunikation; 53)Kongress: ESSV 20 (Dresden : 2009.09.21-23)
Heading toward to the natural way of human-machine interaction - the nimitek project
Vlasenko, Bogdan; Wendemuth, Andreas
In: Konferenz: IEEE International Conference on Multimedia and Expo, New York, NY, USA, 28 June 2009 - 03 July 2009, IEEE International Conference on Multimedia and Expo, 2009 - Piscataway, NJ: IEEE . - 2009, S. 950-953
Application of HMMs for the recognition of emotional sequences in the valence-arousal space
Hübner, David; Böck, Ronald; Wendemuth, Andreas
In: Tagungsband der 20. Konferenz, Dresden, 21. bis 23. September 2009 - Dresden: TUDpress; Hoffmann, Rüdiger . - 2009, S. 200-206 - (Studientexte zur Sprachkommunikation; 53)Kongress: ESSV 20 (Dresden : 2009.09.21-23)
Acoustic emotion recognition: a benchmark comparison of performances
Schuller, Björn; Vlasenko, Bogdan; Eyben, Florian; Rigoll, Gerhard; Wendemuth, Andreas
In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, ASRU 2009 . - Piscataway, NJ : IEEE, ISBN 978-1-424-45479-2, S. 552-558Kongress: ASRU 2009; (Merano) : 2009.12.13-17
Article in conference proceedings
Approach to a design of experiments for sound quality evaluations of car interior adjusting noises
Scheibner, Philipp; Wendemuth, Andreas
In: SAE 2009 Noise and Vibration Conference and Exhibition . - Warrendale, Pa. : SAE International, insges. 6 S.Kongress: SAE Noise and Vibration Conference and Exhibition; (St. Charles, Ill.) : 2009.05.19-21[SAE technical paper 2009-01-2184]
Original article in peer-reviewed periodical-type series
Processing affected speech within human machine interaction
Vlasenko, Bogdan; Wendemuth, Andreas
In: Proceedings of Interspeech 2009 . - ISCA, S. 2039-2042Kongress: Interspeech 2009; 10 (Brighton, UK) : 2009.09.06-10
Analysis of merge criteria within a watershed based segmentation algorithm
Grosser, Tobias; Hellwich, Olaf; Wendemuth, Andreas
In: 2nd International Conference on Adaptive Science & Technology, ICAST 2009 . - IEEE, ISBN 978-1-424-43523-4, S. 250-256Kongress: ICAST; 2 (Ghana) : 2009.12.14-16
2008
Book chapter
Hierarchical HMM-based semantic concept labeling model
Mengistu, Kinfe Tadesse; Hannemann, Mirko; Baum, Tobias; Wendemuth, Andreas
In: 2008 IEEE Workshop on Spoken Language Technology . - Piscataway, N.J : IEEE Service Center, ISBN 978-1-424-43472-5, S. 57-60Kongress: IEEE Workshop on Spoken Language Technology; (Goa, India) : 2008.12.15-18
Using more context in HMM-based semantic tagging model
Mengistu, Kinfe T.; Hannemann, Mirko; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 79-86, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
Survey of state-of-the-art speech recognition technology
Grosser, Tobias; Böck, Ronald; Hübner, David; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers - Düsseldorf, Germany, May 16 - 17, 2008 ; 3rd joined research workshop between Otto-von-Guericke University Magdeburg and the University of Applied Sciences FH Düsseldorf: Düsseldorf, Germany, May 16 - 17, 2008 ; 3rd joined research workshop between Otto-von-Guericke University Magdeburg and the University of Applied Sciences FH Düsseldorf/ Workshop on Emotion, Speech and Face Recognition with Advanced Classifiers - Magdeburg: Univ.; Wendemuth, Andreas . - 2008, S. 73-78Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers 3 (Düsseldorf, Germany : 2008.05.16-17)
Neurobiologically inspired companion systems
Wendemuth, Andreas; Glüge, Stefan; Hamid, Oussama
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 57-66, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
Methods for the reduction of complexity of subjective attributes in the field of sound quality evaluations
Scheibner, Philipp; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 49-55, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
Emotional speech in robot controlling
Böck, Ronald; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers - Düsseldorf, Germany, May 16 - 17, 2008 ; 3rd joined research workshop between Otto-von-Guericke University Magdeburg and the University of Applied Sciences FH Düsseldorf: Düsseldorf, Germany, May 16 - 17, 2008 ; 3rd joined research workshop between Otto-von-Guericke University Magdeburg and the University of Applied Sciences FH Düsseldorf/ Workshop on Emotion, Speech and Face Recognition with Advanced Classifiers - Magdeburg: Univ.; Wendemuth, Andreas . - 2008, S. 29-37Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers 3 (Düsseldorf, Germany : 2008.05.16-17)
Dynamic Bayesian Networks and Hidden Markov Models for modeling situations
Hübner, David; Grosser, Tobias; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 23-28, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
A dual formulation to the Lipschitz Classifier
Stuhlsatz, André; Meier, Hans-Günter; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 1-6, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
Towards user group dependent acoustic models
Mengistu, Kinfe Tadesse; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung . - Dresden : TUDpress, ISBN 978-3-940046-90-1, S. 64-71; Studientexte zur Sprachkommunikation; 50, 2008
Combining speech recognition and acoustic word emotion models for robust text-independent emotion recognition
Schuller, Björn; Vlasenko, Bogdan; Arsic, Dejan; Rigoll, Gerhard; Wendemuth, Andreas
In: 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 . - Piscataway, NJ : IEEE Service Center, ISBN 978-1-424-42571-6, S. 1333-13337Kongress: ICME 2008; (Hannover) : 2008.06.23-26
Role of phonetic content variation for acoustic emotion recognition
Vlasenko, Bogdan; Wendemuth, Andreas
In: Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers. - Magdeburg : Univ., S. 67-72, 2008Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers; 3 (Düsseldorf, Germany) : 2008.05.16-17
Editor
Proceedings of the Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers - Düsseldorf, Germany, May 16 - 17, 2008 ; 3rd joined research workshop between Otto-von-Guericke University Magdeburg and the University of Applied Sciences FH Düsseldorf
Wendemuth, Andreas; Meier, Hans-Günter
In: Magdeburg: Univ., 2008, 86 S., Ill., graph. Darst.Kongress: Workshop on Emotion-, Speech- and Face Recognition with Advanced Classifiers 3 (Düsseldorf : 2008.05.16-17)
Article in conference proceedings
Making the Lipschitz classifier practical via semi-infinite programming
Stuhlsatz, André; Meier, Hans-Günter; Wendemuth, Andreas
In: 2008 International Conference on Machine Learning and Applications . - Piscataway, NJ : IEEE, ISBN 978-1-424-44061-0, S. 40-47Kongress: ICMLA; 7 (San Diego, Calif.) : 2008.12.11-13
Using prior domain knowledge to build robust HMM-based semantic tagger trained on completely unannotated data
Tadesse Mengistu, Kinfe; Hannemann, Mirko; Baum, Tobias; Wendemuth, Andreas
In: Proceedings of the Workshop on Prior Knowledge for Text and Language Processing. - Helsinki, S. 31-36, 2008Kongress: Workshop on Prior Knowledge for Text and Language Processing; (Helsinki) : 2008.07.09
Original article in peer-reviewed periodical-type series
Neurobiologically inspired, multimodal intention recognition for technical communication systems (NIMITEK)
Wendemuth, Andreas; Braun, Jochen; Michaelis, Bernd; Ohl, Frank; Rösner, Dietmar; Scheich, Henning; Warnemünde, Ralf
In: Perception in multimodal dialogue systems . - Berlin [u.a.] : Springer, ISBN 3-540-69368-8, S. 141-145; Lecture notes in computer science; 5078, 2008Kongress: PIT; 4 (Kloster Irsee) : 2008.06.16-18
On the influence of phonetic content variation for acoustic emotion recognition
Vlasenko, Bogdan; Schuller, Björn; Wendemuth, Andreas; Rigoll, Gerhard
In: Perception in multimodal dialogue systems . - Berlin [u.a.] : Springer, ISBN 3-540-69368-8, S. 217-221; Lecture notes in computer science; 5078, 2008Kongress: PIT; 4 (Kloster Irsee) : 2008.06.16-18
Balancing spoken content adaptation and unit length in the recognition of emotion and interest
Vlasenko, Bogdan; Schuller, Björn; Mengistu, Kinfe Tadesse; Rigoll, Gerhard; Wendemuth, Andreas
In: Proceedings of Interspeech 2008 incorporating SST 2008 . - Rundle Mall : Causal Productions, S. 805-808Kongress: INTERSPEECH 2008; 9 (Brisbane, Australia) : 2008.09.22-26SST 2008; 12 (Brisbane, Australia) : 2008.09.22-26
Accent and channel adaptation for use in a telephone-based spoken dialog system
Mengistu, Kinfe Tadesse; Wendemuth, Andreas
In: Text, speech and dialogue . - Berlin [u.a.] : Springer, ISBN 3-540-87390-2, S. 403-410; Lecture notes in computer science; 5246, 2008Kongress: TSD; 11 (Brno) : 2008.09.08-12
2007
Book chapter
Support vector machines as acoustic models in speech recognition
Krüger, Sven E.; Schafföner, Martin; Katz, Marcel; Andelić, Edin; Wendemuth, Andreas
In: Fortschritte der Akustik - Berlin: Dt. Ges. für Akustik . - 2007, insges. 2 S.Kongress: DAGA 33 (Stuttgart : 2007.03.19-22)
Comparing one and two-stage acoustic modeling in the recognition of emotion in speech
Schuller, Björn; Vlasenko, Bogdan; Minguez, Ricardo; Rigoll, Gerhard; Wendemuth, Andreas
In: 2007 IEEE Workshop on Automatic Speech Recognition and Understanding - Piscataway, NJ: IEEE Operations Center . - 2007, S. 596-600Kongress: ASRU 2007 (Kyoto, Japan : 2007.12.09-13)
Acoustic modeling for a speaker-independent telephone-based spoken dialog system
Tadesse Mengistu, Kinfe; Katz, Marcel; Wendemuth, Andreas
In: The XII International Conference "Speech and Computer", SPECOM 2007 ; Vol. 2 - Moscow; Potapova, R. K. Vol. 2 . - 2007, S. 469-474Kongress: SPECOM 2007 12 (Moscow : 2007.10.15-18)
Discriminative Kernel classifiers in speaker recognition
Katz, Marcel; Schafföner, Martin; Andelić, Edin; Krüger, Sven E.; Wendemuth, Andreas
In: Fortschritte der Akustik - Berlin: Dt. Ges. für Akustik . - 2007, insges. 2 S.Kongress: DAGA 33 (Stuttgart : 2007.03.19-22)
Tuning Hidden Markov model for speech emotion recognition
Vlasenko, Bogdan; Wendemuth, Andreas
In: Fortschritte der Akustik - Berlin: Dt. Ges. für Akustik . - 2007, insges. 1 S.Kongress: DAGA 33 (Stuttgart : 2007.03.19-22)
Telephone-based spoken dialog system using HTK-based speech recognizer and voiceXML
Tadesse Mengistu, Kinfe; Wendemuth, Andreas
In: Fortschritte der Akustik - Berlin: Dt. Ges. für Akustik . - 2007, insges. 1 S.Kongress: DAGA 33 (Stuttgart : 2007.03.19-22)
Memory-efficient orthogonal least squares kernel density estimation using enhanced empirical cumulative distribution functions
Schafföner, Martin; Andelić, Edin; Katz, Marcel; Krüger, Sven E.; Wendemuth, Andreas
In: Proceedings of the eleventh International Conference on Artificial Intelligence and Statistics - omnipress . - 2007, insges. 8 S.Kongress: International Conference on Artificial Intelligence and Statistics 11 (San Juan : 2007.03.21-24)
Score calibrating for speaker recognition based on support vector machines and gaussian mixture models
Katz, Marcel; Schafföner, Martin; Krüger, Sven E.; Wendemuth, Andreas
In: Proceedings of the Ninth IASTED International Conference on Signal and Image Processing - Iasted . - 2007, insges. 6 S.Kongress: SIP (Honolulu, Hawaii : 2007.08.20-22)
Gender recognition and Gender-based acoustic model adaptation for telephone-based spoken dialog system
Tadesse Mengistu, Kinfe; Schafföner, Martin; Wendemuth, Andreas
In: Elektronische Sprachsignalverarbeitung - Dresden . - 2007, insges. 8 S.Kongress: Konferenz "ESSV 2007" 18 (Cottbus : 2007.09.10-12)
Combining frame and turn-level information for robust recognition of emotions within speech
Vlasenko, Bogdan; Schuller, Björn; Wendemuth, Andreas; Rigoll, Gerhard
In: Eighth Annual Conference of the International Speech Communication Association - ISCA . - 2007, S. 2249-2253Kongress: Annual Conference of the International Speech Communication Association 8 (Antwerp, Belgium : 2007.08.27-31)
Article in conference proceedings
Updates for nonlinear discriminants
Andelić, Edin; Schafföner, Martin; Katz, Marcel; Krüger, Sven E.; Wendemuth, Andreas
In: Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 - IJCAI . - 2007, insges. 6 S.Kongress: IJCAI 19 (Hyderabad, India : 2007.01.06-12)
Due to technical reasons only 200 publications can be displayed.
View more in the research portal.
- Nahverkehrsservice Sachsen-Anhalt GmbH
- Verhaltensteuerung
- Emotionserkennung
Signal- und Sprachverarbeitung
- Signalverarbeitung
- Sprachverarbeitung
- Klassifikation
- Datenbankabfrage / data base query
- Gerätesteuerung, mit automatischer Sprachverarbeitung
Computational Neuroscience
- Signalverarbeitung
- Sprachverarbeitung
- Klassifikation
- Datenbankabfrage / data base query
- Gerätesteuerung, mit automatischer Sprachverarbeitung
Verhaltensmodellierung
Companion-Systeme
Computational Neuroscience
1984-1994 | Studium und Promotion, Physik und Elektrotechnik. Abschlüsse: |
1988 | Master of Science, University of Miami, Fl. (USA) |
1991 | Diplom-Physiker, Universität Gießen |
1994 | Diplom-Ingenieur Elektrotechnik, FernUniversität Hagen |
1994 | Promotion zum D.Phil. (Dr. rer. nat.), University of Oxford (UK) |
1993-1995 | Postdoctoral Research Fellow (Marie Curie), University of Oxford (UK) |
1995-2001 | Wissenschaftler, Man-Machine-Interfaces, Philips Forschungslaboratorien Aachen |
seit 2001 | Professor für Kognitive Systeme, Universität Magdeburg |
2005/6 & 2012/13 | Institutsleiter Institut für Informations- und Kommunikationstechnik |
2005-2008 | gewählter Universitätssenator |
2005-2010 | Sprecher des Verbundprojekts NIMITEK im Rahmen der Exzellenzförderung des Landes Sachsen-Anhalt: Neurobiologisch inspirierte, multimodale Intentionserkennung für technische Kommunikationssysteme (mit Ohl, Scheich, Rösner, Michaelis) |
2007-2017 | Gründungsmitglied, Mitglied des Direktoriums, Center for Behavioral Brain Sciences (www.med.uni-magdeburg.de/neuromd/) |
2009-2018 | stellv. Sprecher und Koordinator des Standortes Magdeburg: SFB/Transregio 62 "Eine Companion-Technologie für Kognitive Technische Systeme" (www.sfb-trr-62.de) |