Title :
Speech emotion recognition based on re-composition of two-class classifiers
Author :
Huang, Chengwei ; Jin, Yun ; Zhao, Yan ; Yu, Yinhua ; Zhao, Li
Author_Institution :
Southeast Univ., Nanjing, China
Abstract :
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.
Keywords :
emotion recognition; pattern classification; speech recognition; correlation decoder; emotion classes; feature optimization; feature selection; multiple emotions classification; n-class classifier; speech emotion recognition; two-class classifiers; Decoding; Emotion recognition; Error analysis; Humans; Speech;
Conference_Titel :
Affective Computing and Intelligent Interaction and Workshops, 2009. ACII 2009. 3rd International Conference on
Conference_Location :
Amsterdam
Print_ISBN :
978-1-4244-4800-5
Electronic_ISBN :
978-1-4244-4799-2
DOI :
10.1109/ACII.2009.5349420
