Analysis of compressed speech signals in an Automatic Speaker Recognition system

Author

Metzger, Richard A. ; Doherty, John F. ; Jenkins, David M.

Author_Institution

Dept. of Electr. Eng., Pennsylvania State Univ., State College, PA, USA

fYear

2015

fDate

18-20 March 2015

Firstpage

1

Lastpage

5

Abstract

This paper analyzes the effects popular audio compression algorithms have on the performance of a speaker recognition system. Popular audio compression algorithms were used to compress both clean and noisy speech before being passed to a speaker recognition system. The features extracted from each speaker were 19-dimensional Mel-Frequency Cepstrum Coefficients (MFCC) and the corresponding features were modeled using a 16 mixture Gaussian Mixture Model (GMM). Our experiments show that compression will have a negative effect on recognition rates if the compressed speech is clean. However, if small amounts of white Gaussian noise are added before the speech is compressed, recognition rates can be increased by as much as 7% with certain compression algorithms.

Keywords

Gaussian noise; Gaussian processes; audio coding; cepstral analysis; data compression; feature extraction; mixture models; speaker recognition; speech coding; Gaussian mixture model; MFCC; audio compression algorithms; automatic speaker recognition system; compressed speech signal analysis; feature extraction; mel-frequency cepstrum coefficients; white Gaussian noise; Compression algorithms; Digital audio players; Hidden Markov models; Signal to noise ratio; Speech; Speech recognition; Audio Compression; Gaussian Mixture Models; Mel-Frequency Cepstrum Coefficients; Speaker Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Sciences and Systems (CISS), 2015 49th Annual Conference on

Conference_Location

Baltimore, MD

Type

conf

DOI

10.1109/CISS.2015.7086817

Filename

7086817