A Study on Emotional Feature Analysis and Recognition in Speech Signal
This paper analysis the feather of the time, amplitude, pitch and formant construction involved such four emotions as happiness, anger, surprise and sorrow. Through comparison with non-emotional quiet speech signal, we sum up the distribution law of emotional feather including different emotional speech. Nine emotional features were extracted form emotional speech for recognizing emotion. We introduce two emotional recognition methods based on principal component analysis and the results show that these method can provide an effective solution to emotional recognition.
speech signal smotional feature emotional recognition
Xin min Cheng Pei ying Cheng Li Zhao
School of Inforrnation Engineering Huzhou Teachers College Huzhou,Zhejiang Province,China Department of Radio Engineering Southeast University Nanking,China
国际会议
长沙
英文
418-420
2009-04-11（万方平台首次上网日期，不代表论文的发表时间）