Framework for VOIP speech database generation and a comparaison of different features extraction methodes for speaker identification on VOIP

Author

Imen, El-Taani ; Imen, Amrous Anissa ; Debyeche, Mohamed

Author_Institution

Speech Commun. & Signal Process. Lab. (LPCTS), USTHB, Algiers, Algeria

fYear

2015

fDate

25-27 May 2015

Firstpage

1

Lastpage

5

Abstract

This paper presents a framework for VOIP database generation and an investigation of the impact of VOIP characteristics on the accuracy of automatic speaker identification system. Exactly we study the impact of G711 and iLBC codec, and the influence of packet loss. A set of experiments are done on the generated databases to find the best feature extraction method for speaker identification on VOIP. The acoustic features considered are the most commonly used ones: MFCCs, LPCs and PLPs. Speaker models used in this study are based on Gaussian Mixture models and are implemented using HTK. VOIP databases used for training and testing are created using Asterisk.

Keywords

Gaussian processes; Internet telephony; audio databases; cepstral analysis; feature extraction; mixture models; speaker recognition; speech codecs; Asterisk; G711 codec; Gaussian mixture model; HTK; LPC; MFCC; PLP; VOIP characteristics; VOIP database generation; VOIP speech database generation; acoustic feature; automatic speaker identification system; features extraction method; generated database; iLBC codec; packet loss; speaker model; Acoustics; Codecs; Databases; Feature extraction; Internet telephony; Packet loss; Speech; Asterisk; GMM; LPC; MFCC; PLP; VOIP; speaker identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Control, Engineering & Information Technology (CEIT), 2015 3rd International Conference on

Conference_Location

Tlemcen

Type

conf

DOI

10.1109/CEIT.2015.7233101

Filename

7233101