A study about MFCC relevance in emotion classification for SRoL database

Author

Dan, Zbancioc Marius ; Monica, Feraru Silvia

Author_Institution

Inst. of Comput. Sci., Tech. Univ. “Gheorghe Asachi” of Iasi, Iasi, Romania

fYear

2013

fDate

11-13 Oct. 2013

Firstpage

1

Lastpage

4

Abstract

The focus of this paper is to establish the relevance of MFCC coefficients in the emotion recognition for Romanian language, comparing with prosodic features: F0 fundamental frequency, F1-F4 formants, jitter and shimmer. We noted that the accuracy recognition rate is improved by using MFCC feature vectors around 90%. In our previous works we obtained only 65% percent in emotion classification with feature vectors which contain F0, F1-F4 formats, jitter and shimmer. We also studied the relevance of the derivative ΔMFCC and ΔΔMFCC. The obtained results are remarkable considering that the SRoL database contains only “normal” voices. In literature, similar performance is reported usually on the databases with professional voices.

Keywords

audio databases; cepstral analysis; emotion recognition; feature extraction; jitter; natural language processing; ΔΔMFCC relevance; F0 fundamental frequency; F1-F4 formants; MFCC coefficient relevance; MFCC feature vectors; Mel-frequency cepstral coefficients; Romanian language; SRoL database; derivative ΔMFCC relevance; emotion classification; emotion recognition; jitter; normal voices; professional voices; prosodic feature vectors; shimmer; MFCC coefficient; emotion classificatio; prosodic feature; weighted KNN;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Electronics Engineering (ISEEE), 2013 4th International Symposium on

Conference_Location

Galati

Type

conf

DOI

10.1109/ISEEE.2013.6674323

Filename

6674323