Home page for BjoernSchuller

I am a senior researcher and lecturer in Speech Processing and Pattern Recognition at the Technische Universitaet Muenchen (Munich University of Technology), Germany and visiting scientist at the CNRS-LIMSI in Orsay, France. Since 2000 I am working in the field of Emotion Recognition, and since 2007 I am elected member of the HUMAINE Association Executive Committee. Currently, I am running the Special Interest Group on Emotion Recognition from Speech (SIG-Speech), am a member and secretary of our Transactions on Affective Computing steering committee, guest edit two special issues on Emotion and Speech in the Speech Communication and Advances in Signal Processing journals, and co-organise a Workshop on EMOTION at LREC 2010. Past organisation includes the INTERSPEECH 2009 Emotion Challenge on recognition of emotion from speech co-sponsored by our association. Please have a look.

Current topics of my research interests are:

Provision of tools to the community, as the open Emotion and Affect Recognition Toolkit ("openEAR").

Multimodal Recognition of Emotion, foremostly by speech and text analysis

Affect-robust Automatic Speech Recognition

Recognition of non-linguistic vocalisations as laughter

Mood in Music

Novel machine learning architectures (e.g. Tandem BLSTM-DBN)

Standardization issues in AER.

Please feel free to contact me via schuller at tum.de or schuller at IEEE.org or find more details about publications, reviewing, program committee, and general membership activities here.

Some Selected Recent Publications:

Björn Schuller, Martin Wöllmer, Florian Eyben, Gerhard Rigoll: "Retrieval of Paralinguistic Information in Broadcasts”, in Multimedia Information Extraction, Mark Maybury (ed.), MIT Press, Cambridge, Massachusetts, 2010.

Björn Schuller, Ronald Müller, Florian Eyben, Jürgen Gast, Benedikt Hörnler, Martin Wöllmer, Gerhard Rigoll, Anja Höthker, Hitoshi Konosu: "Being Bored? Recognising Natural Interest by Extensive Audiovisual Integration for Real-Life Application", Image and Vision Computing Journal (IMAVIS), Special Issue on Visual and Multimodal Analysis of Human Spontaneous Behavior, Elsevier, Vol. 27, Issue 12, pp. 1760-1774, November 2009.

Björn Schuller, Clemens Hage, Dagmar Schuller, Gerhard Rigoll: "'Mister D.J., Cheer Me Up!': Musical and Textual Features for Automatic Mood Classification", Journal of New Music Research, Taylor & Francis, Vol. 38, Issue 4, 33 pages, 2009.

Björn Schuller, Martin Wöllmer, Florian Eyben, Gerhard Rigoll: "Spectral or Voice Quality? Feature Type Relevance for the Discrimination of Emotion Pairs", in The Role of Prosody in Affective Speech, Linguistic Insights, Studies in Language and Communication, Vol. 97, Slyvie Hancil (ed.), Peter Lang Publishing Group, ISBN 978-3-03911-696-6, 2009.

Björn Schuller, Johannes Dorfner, Gerhard Rigoll: "Determination of Non-Prototypical Valence and Arousal in Popular Music: Features and Performances", EURASIP Journal on Audio, Speech, and Music Processing, Special Issue on "Scalable Audio-Content Analysis", 2010.

Björn Schuller, Stefan Steidl, Anton Batliner: "The Interspeech 2009 Emotion Challenge", in Proc. Interspeech (2009), ISCA, Brighton, UK, ISSN 1990-9772, pp. 312-315, 06.-10.09.2009.

Björn Schuller, Joachim Schenk, Gerhard Rigoll, Tobias Knaup: "“The Godfather” vs. “Chaos”: Comparing Linguistic Analysis based on Online Knowledge Sources and Bags-of-N-Grams for Movie Review Valence Estimation", Proc. International Conference on Document Analysis and Recognition (ICDAR 2009), IAPR, IEEE Computer Society, pp. 858-862, Barcelona, Spain, 26.07.-29.07.2009.

Björn Schuller, Anton Batliner, Stefan Steidl, Dino Seppi: "Emotion Recognition from Speech: Putting ASR in the Loop", in Proc. ICASSP 2009, IEEE, pp. 4585-4588, Taipei, Taiwan, 19.-24.04.2009.