Combining GMM's with support vector machines for text-independent speaker verification

Jamal Kharroubi; Dijana Petrovska-Delacrétaz; Gérard Chollet

Combining GMM's with support vector machines for text-independent speaker verification

Jamal Kharroubi
, Dijana Petrovska-Delacrétaz
, Gérard Chollet

Department of Image and Signal Processing
CNRS LTCI

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

14 Citations (Scopus)

Résumé

Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched (train/test) conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing [2], [3], [4] and for the fusion of experts in biometric authentification [5]. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.

langue originale	Anglais
titre	EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
rédacteurs en chef	Borge Lindberg, Henrik Benner, Paul Dalsgaard, Zheng-Hua Tan
Editeur	International Speech Communication Association
Pages	1761-1764
Nombre de pages	4
ISBN (Electronique)	8790834100, 9788790834104
état	Publié - 1 janv. 2001
Modification externe	Oui
Evénement	7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Danemark Durée: 3 sept. 2001 → 7 sept. 2001

Série de publications

Nom	EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Une conférence

Une conférence	7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
Pays/Territoire	Danemark
La ville	Aalborg
période	3/09/01 → 7/09/01

Contient cette citation

Kharroubi, J., Petrovska-Delacrétaz, D., & Chollet, G. (2001). Combining GMM's with support vector machines for text-independent speaker verification. Dans B. Lindberg, H. Benner, P. Dalsgaard, & Z.-H. Tan (eds.), EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology (p. 1761-1764). (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology). International Speech Communication Association.

Kharroubi, Jamal ; Petrovska-Delacrétaz, Dijana ; Chollet, Gérard. / Combining GMM's with support vector machines for text-independent speaker verification. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. Editeur / Borge Lindberg ; Henrik Benner ; Paul Dalsgaard ; Zheng-Hua Tan. International Speech Communication Association, 2001. p. 1761-1764 (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

@inproceedings{8da2972730774e2098f05cd42394cd85,

title = "Combining GMM's with support vector machines for text-independent speaker verification",

abstract = "Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched (train/test) conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing [2], [3], [4] and for the fusion of experts in biometric authentification [5]. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.",

author = "Jamal Kharroubi and Dijana Petrovska-Delacr{\'e}taz and G{\'e}rard Chollet",

year = "2001",

month = jan,

day = "1",

language = "English",

series = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",

publisher = "International Speech Communication Association",

pages = "1761--1764",

editor = "Borge Lindberg and Henrik Benner and Paul Dalsgaard and Zheng-Hua Tan",

booktitle = "EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology",

note = "7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 ; Conference date: 03-09-2001 Through 07-09-2001",

}

Kharroubi, J, Petrovska-Delacrétaz, D & Chollet, G 2001, Combining GMM's with support vector machines for text-independent speaker verification. Dans B Lindberg, H Benner, P Dalsgaard & Z-H Tan (eds), EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology, International Speech Communication Association, p. 1761-1764, 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001, Aalborg, Danemark, 3/09/01.

Combining GMM's with support vector machines for text-independent speaker verification. / Kharroubi, Jamal; Petrovska-Delacrétaz, Dijana; Chollet, Gérard.
EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. Ed. / Borge Lindberg; Henrik Benner; Paul Dalsgaard; Zheng-Hua Tan. International Speech Communication Association, 2001. p. 1761-1764 (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

TY - GEN

T1 - Combining GMM's with support vector machines for text-independent speaker verification

AU - Kharroubi, Jamal

AU - Petrovska-Delacrétaz, Dijana

AU - Chollet, Gérard

PY - 2001/1/1

Y1 - 2001/1/1

N2 - Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched (train/test) conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing [2], [3], [4] and for the fusion of experts in biometric authentification [5]. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.

AB - Current best performing speaker recognition algorithms are based on Gaussian Mixture Models (GMM). Their results are not satisfactory for all experimental conditions, especially for the mismatched (train/test) conditions. Support Vector Machine is a new and very promissing technique in statistical learning theory. Recently, this technique produced very interesting results in image processing [2], [3], [4] and for the fusion of experts in biometric authentification [5]. In this paper we address the issue of using the Support Vector Learning technique in combination with the currently well performing GMM models, in order to improve speaker verification results.

M3 - Conference contribution

AN - SCOPUS:85009112344

T3 - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

SP - 1761

EP - 1764

BT - EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

A2 - Lindberg, Borge

A2 - Benner, Henrik

A2 - Dalsgaard, Paul

A2 - Tan, Zheng-Hua

PB - International Speech Communication Association

T2 - 7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001

Y2 - 3 September 2001 through 7 September 2001

ER -

Kharroubi J, Petrovska-Delacrétaz D, Chollet G. Combining GMM's with support vector machines for text-independent speaker verification. Dans Lindberg B, Benner H, Dalsgaard P, Tan ZH, rédacteurs en chef, EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology. International Speech Communication Association. 2001. p. 1761-1764. (EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology).

Combining GMM's with support vector machines for text-independent speaker verification

Résumé

Série de publications

Une conférence

Empreinte digitale

Contient cette citation