Emotion-detecting Based Model Selection for Emotional Speech Recognition

Author

Pan, Y.C. ; Xu, M.X. ; Liu, L.Q. ; Jia, P.F.

Author_Institution

Center for Speech Technol., Tsinghua Univ., Beijing

Volume

2

fYear

2006

fDate

4-6 Oct. 2006

Firstpage

2169

Lastpage

2172

Abstract

As known to all, the performance of speech recognition degrades dramatically in the presence of emotion. How to deal with emotion issue properly is crucial. Most widely used approaches include robust feature extraction, speaker normalization and model tuning/retraining. In the study, a novel method is proposed, that is, adaptation technique is adopted to transform a general model into emotion-specific one with a small amount of emotion speech. Moreover, a model-selection strategy based on emotion-detection was proposed and proven to be effective, and the overall mean recognition rate increased to 80.79% with an Error Rate Reduction (ERR) of 16.55% compared to the neutral speech Acoustic Model (AM).

Keywords

emotion recognition; error analysis; feature extraction; speaker recognition; emotion speech; emotion-detection; emotional speech recognition; error rate reduction; feature extraction; mean recognition rate; model-selection strategy; neutral speech acoustic model; speaker normalization; Acoustic distortion; Degradation; Emotion recognition; Loudspeakers; Phase distortion; Robustness; Speech recognition; Speech synthesis; Vocabulary; Working environment noise; adaptation; emotion-detection; emotional speech; model-selection; speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Engineering in Systems Applications, IMACS Multiconference on

Conference_Location

Beijing

Print_ISBN

7-302-13922-9

Electronic_ISBN

7-900718-14-1

Type

conf

DOI

10.1109/CESA.2006.4281997

Filename

4281997