11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Determining Optimal Features for Emotion Recognition from Speech by Applying an Evolutionary Algorithm

David Hübner, Bogdan Vlasenko, Tobias Grosser, Andreas Wendemuth

Otto-von-Guericke-Universität Magdeburg, Germany

The automated recognition of emotions from speech is a challenging issue. In order to build an emotion recognizer well defined features and optimized parameter sets are essential. This paper will show how an optimal parameter set for HMM-based recognizers can be found by applying an evolutionary algorithm on standard features in automated speech recognition. For this, we compared different signal features, as well as several architectures of HMMs. The system was evaluated on a non-acted database and its performance was compared to a baseline system. We present an optimal feature set for the public part of the SmartKom database.

Full Paper

Bibliographic reference.  Hübner, David / Vlasenko, Bogdan / Grosser, Tobias / Wendemuth, Andreas (2010): "Determining optimal features for emotion recognition from speech by applying an evolutionary algorithm", In INTERSPEECH-2010, 2358-2361.