Automatic speaker recognition for mobile communications using AMR-WB speech coding

Author

Fedila, Meriem ; Amrouche, Abderrahmane

Author_Institution

Speech Commun. & Signal Process. Lab., USTHB, Algiers, Algeria

fYear

2012

fDate

2-5 July 2012

Firstpage

1034

Lastpage

1038

Abstract

The aim of this paper is to investigate the influence of Adaptative Multi-Rate Wideband (AMR-WB) speech coding on Distributed Speaker Recognition (DSR). The main goal is to improve speaker recognition performance without resynthesizing the speech waveform in mobile communications. For this purpose, we have implemented a method in order to extract the acoustic features in the compressed domain, directly from encoded bitstream. The obtained results, using ARADIGIT database, show that the proposed approach, with GMM and SVM models, using ISF (Immittance Spectral Frequency) parameters through a noised channel (AWGN and Rayleigh) are promising.

Keywords

AWGN channels; Rayleigh channels; mobile communication; speaker recognition; speech coding; support vector machines; waveform analysis; AMR-WB speech coding; ARADIGIT database; AWGN channel; DSR; GMM models; ISF parameters; Rayleigh channel; SVM models; acoustic features extraction; adaptative multirate wideband speech coding; automatic speaker recognition; distributed speaker recognition; immittance spectral frequency parameters; mobile communications; noised channel; speech waveform; Databases; Feature extraction; Speaker recognition; Speech; Speech coding; Support vector machines; Vectors; AMR-WB; GMM; ISF; Robust DSR; SVM; Speaker Identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on

Conference_Location

Montreal, QC

Print_ISBN

978-1-4673-0381-1

Electronic_ISBN

978-1-4673-0380-4

Type

conf

DOI

10.1109/ISSPA.2012.6310441

Filename

6310441