A Study on Emotional Feature Analysis and Recognition in Speech

PDF(379 KB)

ACTA ELECTRONICA SINICA ›› 2004, Vol. 32 ›› Issue (4) : 606-609.

论文

A Study on Emotional Feature Analysis and Recognition in Speech

ZHAO Li^1,2, JIANG Chun-hui^1,2, ZOU Cai-rong¹, WU Zhen-yang¹

Author information +

History +

Abstract

This paper presents a new emotion recognition method based on the hybrid feature and MMD.The hybrid feature was composed of global and time sequence.Experiments were conducted on a task of 10 speakers' 1000 sentences including happy,angry,surprising and sorrowful emotions to demonstrate has effectiveness of the new method.The average emotion recognition rate was reached as higher as 94%.

Key words

speech signal / emotional feature analysis / MMD / emotion recognition

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHAO Li;JIANG Chun-hui;ZOU Cai-rong;WU Zhen-yang. A Study on Emotional Feature Analysis and Recognition in Speech[J]. Acta Electronica Sinica, 2004, 32(4): 606-609.