Pitch and Energy Contribution in Emotion and Speaking styles Recognition Enhancement

Author

Kammoun, M. ; Ellouze, N.

Author_Institution

Signal, Image & Pattern Recognition Lab., National Sch. of Eng. of Tunis

Volume

1

fYear

2006

fDate

4-6 Oct. 2006

Firstpage

97

Lastpage

100

Abstract

This paper highlights the influence of some prosodic features in enhancing the recognition accuracies of emotions and speaking styles in speech. In this work, we seek to recognize 10 emotions and speaking styles based on real speech. After having extracted a large amount of cues, we use the hidden Markov models classifier. Results are given on text-independent emotion recognition using SUSAS database. The aim of this work is to test the influence of energy and pitch in emotion recognition. Throughout this study, MFCC, log energy and pitch frequency, are used as the base features. The obtained recognition accuracy for 10 different emotions and speaking styles exceeds 85% reaching 89.35% for the slow style using the best combination of spectral and prosodic features

Keywords

emotion recognition; hidden Markov models; speaker recognition; speech enhancement; SUSAS database; emotion recognition enhancement; energy contribution; hidden Markov models classifier; log energy; pitch contribution; pitch frequency; prosodic feature; real speech; speaking styles recognition enhancement; spectral feature; Emotion recognition; Hidden Markov models; Laboratories; Pattern recognition; Spatial databases; Speech analysis; Speech enhancement; Speech processing; Speech recognition; Stress; Hmm classifier; emotion and speaking style; log energy; mfcc; pitch;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Engineering in Systems Applications, IMACS Multiconference on

Conference_Location

Beijing

Print_ISBN

7-302-13922-9

Electronic_ISBN

7-900718-14-1

Type

conf

DOI

10.1109/CESA.2006.4281631

Filename

4281631