Research on a New Kind of Speech Parameter Based on MFCC

Author

Xiaoyan Wang

Author_Institution

Office of Acad. Affairs, Shaanxi Radio & TV Univ., Xi´an, China

fYear

2012

fDate

2-4 Nov. 2012

Firstpage

513

Lastpage

516

Abstract

Based on Anindya Roy´s research, this paper suggests a new kind of speech signal feature: second-order weighted Mel Frequency Cepstrum Coefficients by introducing the method of weighted filter bank analysis. It also studies the weighted factor in the process of obtaining the Inverted Mel Frequency Cepstrum Coefficients and presents the optimal weighted factor. The result of the experiments shows that this new parameter is more robust, and can be applied to generic speech recognition system.

Keywords

channel bank filters; speech recognition; MFCC; generic speech recognition system; inverted Mel frequency cepstrum coefficients; optimal weighted factor; second-order weighted Mel frequency cepstrum coefficients; speech parameter; speech signal feature; weighted filter bank analysis; Cepstrum; Feature extraction; Filter banks; Mel frequency cepstral coefficient; Speech; Speech recognition; Mel Frequency Cepstrum Coefficients (MFCC); Inverted Mel Frequency Cepstrum Coefficients (IMFCC); second-order weighted Mel Frequency Cepstrum Coefficients (SO-MFCC); optimal weighted factor;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Information Networking and Security (MINES), 2012 Fourth International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4673-3093-0

Type

conf

DOI

10.1109/MINES.2012.171

Filename

6407398