Personal tools
You are here: Home → Members → BjoernSchuller's Home
Log in


Forgot your password?
 

Home page for BjoernSchuller

Home page of Bjoern Schuller


Björn Schuller
 Technische Universitaet Muenchen 		Key research interests:

Emotion recognition out of acoustic and linguistic information. "Brute-force" generation of large acoustic feature sets and self-learning feature space optimization. Combination of ASR and linguistic analyses as bag-of-words, part-of-speech or string kernels. Diverse multidomal fusion approaches. Emotion recognition in the noise, emotion spotting, "out-of-vocab" emotions, and standardization issues.
I am a senior researcher at Technische Universitaet Muenchen, Germany. Since 2000 I am working in the field of Emotion Recognition. Main topics thereby are:

Acoustic analysis

  • Time Series Analysis of Low-Level-Descriptors to obtain prosodic, articulatory and voice quality high-level features.
  • Feature adaptation to human perception.
  • Speaker and noise adaptation.
  • Applying machine learning techniques as feature-space-optimization by PCA, SFFS, IGR and GA.
  • Extensive classifier evaluation as ANN, SVM, HMM, GM, DBN, RF, DT.
  • "Out-of-vocab" emotions and stream processing.
  • Standardization issues in AER.

    Linguistic analysis

  • Diverse modeling approaches: Feature-Space-Representation, (back-off)N-Grams, Bayesian Nets for Phrasespotting
  • Inclusion of ASR and ASR adaptation to emotional speech.

    Further more I work on emotion recognition out of manual interaction.

    Please feel free to contact me via schuller at tum.de or schuller at IEEE.org or find more details about reviewing, program committee and general membership activities at www.mmk.ei.tum.de/~sch

    Some Selected Recent Publications:

  • B. Schuller, M. Ablaßmeier, R. Müller, S. Reifinger, T. Poitschke, G. Rigoll: "Speech Communication and Multimodal Interfaces", in Advanced Man Machine Interaction, K.-F. Kraiss (ed.), Springer Verlag Berlin, Heidelberg, ISBN: 3-540-30618-8, pp. 141-190, 2006.
  • B. Schuller, A. Batliner, D. Seppi, S. Steidl, T. Vogt, J. Wagner, L. Devillers, L. Vidrascu, N. Amir, L. Kessous, V. Aharonson: "The Relevance of Feature Type for the Automatic Classification of Emotional User States: Low Level Descriptors and Functionals", to appear within Proc. INTERSPEECH 2007, ISCA, Antwerp, Belgium, 27.-31.8.2007.
  • B. Schuller, D. Seppi, A. Batliner, A. Maier, S. Steidl: "Towards More Reality in the Recognition of Emotional Speech", Proc. ICASSP 2007, IEEE, Vol. IV, pp. 941-944, ISBN 1-4244-0728-1, Honolulu, Hawaii, USA, 15.-20.04.2007.
  • B. Schuller, M. Wimmer, D. Arsic, G. Rigoll, B. Radig: "Audiovisual Behavior Modeling by Combined Feature Spaces", Proc. ICASSP 2007, IEEE, Vol. II, pp. 733-736, ISBN 1-4244-0728-1, Honolulu, Hawaii, USA, 15.-20.04.2007.
  • B. Schuller, N. Köhler, R. Müller, G. Rigoll : "Recognition of Interest in Human Conversational Speech", INTERSPEECH 2006, ICSLP, ISCA, pp. 793-796, Pittsburgh, PA, USA, 17.-21.09.2006.
  • B. Schuller, J. Stadermann, G. Rigoll: "Affect-Robust Speech Recognition by Dynamic Emotional Adaptation", Speech Prosody 2006, Special Session Prosody in Automatic Speech Recognition, ISCA, Dresden, Germany, May 2-5, 2006.
  • B. Schuller, D. Arsic, F. Wallhoff, G. Rigoll: "Emotion Recognition in the Noise Applying Large Acoustic Feature Sets", Speech Prosody 2006, ISCA, Dresden, Germany, May 2-5, 2006.
  • B. Schuller, G. Rigoll, M. Lang: "Hidden Markov Model-based Speech Emotion Recognition", ICASSP 2003, IEEE Int. Conference on Acoustics, Speech, and Signal Processing, Feature Extraction Techniques and Applications, Hong Kong, China, Vol. II, pp. 1-4, 2003.
  • B. Schuller: "Towards intuitive speech interaction by the integration of emotional aspects", SMC 2002, IEEE International Conference on Systems, Man and Cybernetics, Yasmine Hammamet, Tunisia, CD-Rom Proceedings, 2002.
    • Document Actions
     
    Powered by Plone

    Portal usage statistics