Share Email Print

Proceedings Paper

A study of speech emotion recognition based on hybrid algorithm
Author(s): Ju-xia Zhu; Chao Zhang; Zhao Lv; Yao-quan Rao; Xiao-pei Wu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

To effectively improve the recognition accuracy of the speech emotion recognition system, a hybrid algorithm which combines Continuous Hidden Markov Model (CHMM), All-Class-in-One Neural Network (ACON) and Support Vector Machine (SVM) is proposed. In SVM and ACON methods, some global statistics are used as emotional features, while in CHMM method, instantaneous features are employed. The recognition rate by the proposed method is 92.25%, with the rejection rate to be 0.78%. Furthermore, it obtains the relative increasing of 8.53%, 4.69% and 0.78% compared with ACON, CHMM and SVM methods respectively. The experiment result confirms the efficiency of distinguishing anger, happiness, neutral and sadness emotional states.

Paper Details

Date Published: 1 October 2011
PDF: 9 pages
Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 82854Y (1 October 2011); doi: 10.1117/12.913366
Show Author Affiliations
Ju-xia Zhu, Anhui Univ. (China)
Chao Zhang, Anhui Univ. (China)
Zhao Lv, Anhui Univ. (China)
Yao-quan Rao, Anhui Univ. (China)
Xiao-pei Wu, Anhui Univ. (China)

Published in SPIE Proceedings Vol. 8285:
International Conference on Graphic and Image Processing (ICGIP 2011)
Yi Xie; Yanjun Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top