Speech emotion recognition based on re-composition of two-class classifiers

A method of using two-class classifiers in emotion recognition was discussed. Emotion classes were divided into pairs for improved feature selection and optimization. Each pair of emotions was classified by a two-class classifier and the final recognition result was reached by a correlation decoder. Compared with n-class classifier, using two-class classifiers for each pair of emotions is more suitable for multiple emotions classification.

[1]  Zhongzhe Xiao,et al.  Features extraction and selection for emotional speech classification , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[2]  Zengfu Wang,et al.  An Emotion Space Model for Recognition of Emotions in Spoken Chinese , 2005, ACII.

[3]  Klaus R. Scherer,et al.  Vocal communication of emotion: A review of research paradigms , 2003, Speech Commun..

[4]  M. Borchert,et al.  Emotions in speech - experiments with prosody and quality features in speech for use in categorical and dimensional emotion recognition environments , 2005, 2005 International Conference on Natural Language Processing and Knowledge Engineering.

[5]  Wei Wu,et al.  GMM Supervector Based SVM with Spectral Features for Speech Emotion Recognition , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[6]  George N. Votsis,et al.  Emotion recognition in human-computer interaction , 2001, IEEE Signal Process. Mag..