Presentation 2006/1/20
Speech Emotion Recognition with the Teager Energy Operator
Katsuya NAOI, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes method for recognizing emotion in speech with the nonlinear operator of the Teager Energy Operator (TEO). Because we think that emotion is a kind of stress, we apply the TEO, which is used for the stress detection, to emotion recognition. We propose the four features calculated by the TEO, i.e. TEO-CB-Auto-Env, TEO-Auto-Env, TEO-FM-Var, TEO-LFPC. In experiments, we compared recognition performances by each of four TEO-based features and the conventional features of pitch and MFCC. We also investigated recognition rate by integrating the four TEO based features and MFCC. We used four kinds of speeches, 62 neutral, 43 joyful, 61 angry, and 51 sad speeches. As a result, we have obtained the average recognition rate of 51%, and maximum rate of 61% in sad emotion. The proposed method, however, misjudge "sadness" for "neutral".
Keyword(in Japanese) (See Japanese page)
Keyword(in English) signal / emotion recognition / nonlinear characteristic / Teager Energy Operator
Paper # SP2005-150
Date of Issue

Conference Information
Committee SP
Conference Date 2006/1/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech Emotion Recognition with the Teager Energy Operator
Sub Title (in English)
Keyword(1) signal
Keyword(2) emotion recognition
Keyword(3) nonlinear characteristic
Keyword(4) Teager Energy Operator
1st Author's Name Katsuya NAOI
1st Author's Affiliation Graduate school of Information Science, Nagoya University()
2nd Author's Name Tetsuya MATSUMOTO
2nd Author's Affiliation Graduate school of Information Science, Nagoya University
3rd Author's Name Yoshinori TAKEUCHI
3rd Author's Affiliation Information Security Promotion Agency, Nagoya University RIKEN, Bio-Mimetic Control Research Center
4th Author's Name Hiroaki KUDO
4th Author's Affiliation Graduate school of Information Science, Nagoya University
5th Author's Name Noboru OHNISHI
5th Author's Affiliation Graduate school of Information Science, Nagoya University
Date 2006/1/20
Paper # SP2005-150
Volume (vol) vol.105
Number (no) 572
Page pp.pp.-
#Pages 6
Date of Issue