Towards More Reality in the Recognition of Emotional Speech
- 1 April 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-941-941
Abstract
As automatic emotion recognition based on speech matures, new challenges can be faced. We therefore address the major aspects in view of potential applications in the field, to benchmark today's emotion recognition systems and bridge the gap between commercial interest and current performances: acted vs. spontaneous speech, realistic emotions, noise and microphone conditions, and speaker independence. Three different data-sets are used: the Berlin Emotional Speech Database, the Danish Emotional Speech Database, and the spontaneous AIBO Emotion Corpus. By using different feature types such as word- or turn-based statistics, manual versus forced alignment, and optimization techniques we show how to best cope with this demanding task and how noise addition or different microphone positions affect emotion recognition.Keywords
This publication has 7 references indexed in Scilit:
- "Of All Things the Measure Is Man" : Automatic Classification of Emotions and Inter-Labeler Consistency2006
- Emotion Recognition from Noisy Speech2006
- Emotion recognition in the noise applying large acoustic feature sets2006
- A database of German emotional speech2005
- Toward detecting emotions in spoken dialogsIEEE Transactions on Speech and Audio Processing, 2005
- Robust Parallel Speech Recognition in Multiple Energy Bands2005
- Emotion recognition in human-computer interactionIEEE Signal Processing Magazine, 2001