Time-Frequency Based Approach for Analysis and Synthesis of Emotional Voice

Author

Kobayashi, Mamoru ; Wada, Shigeo

Author_Institution

Graduate Sch. of Eng., Tokyo Denki Univ.

Volume

2

fYear

2005

fDate

21-24 Nov. 2005

Firstpage

1642

Lastpage

1645

Abstract

In this paper, analysis and synthesis methods of emotional voice for man-machine natural interface is developed. First, the emotional voice (neutral, anger, sadness, joy, dislike) is analyzed using time-frequency representation of speech and similarity analysis. Then, based on the result of emotional analysis, a voice with neutral emotion is transformed to synthesize the particular emotional voice using time-frequency modifications. In the simulations, five types of emotion are analyzed using 50 samples of speech signals. The satisfactory average discrimination rate is achieved in the similarity analysis. Further, the synthesized emotional voice is subjectively evaluated. It is confirmed that the emotional voice is naturally generated by the proposed time-frequency based approach

Keywords

emotion recognition; natural language interfaces; speech processing; speech synthesis; time-frequency analysis; emotional voice synthesis; man-machine natural interface; speech processing; speech signals; time-frequency analysis; Analytical models; Hidden Markov models; Man machine systems; Prototypes; Signal analysis; Signal synthesis; Speech analysis; Speech processing; Speech synthesis; Time frequency analysis; Emotional voice; Speech processing; Time-frequency analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer as a Tool, 2005. EUROCON 2005.The International Conference on

Conference_Location

Belgrade

Print_ISBN

1-4244-0049-X

Type

conf

DOI

10.1109/EURCON.2005.1630285

Filename

1630285