A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION

J. Černocký; D. Petrovska-Delacrétaz; S. Pigeon; Patrick Verlinde; G. Chollet

A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION

J. Černocký, D. Petrovska-Delacrétaz, S. Pigeon, Patrick Verlinde, G. Chollet

Communication, Information, Systems and Sensors

Résultats de recherche: Chapitre dans un livre, un rapport, des actes de conférences › Contribution à une conférence › Revue par des pairs

Résumé

Current text-independent speaker verification systems are usually based on modeling globally the probability density function (PDF) of the speaker feature vectors. In this paper, segmental approaches to text-independent speaker verification are discussed. Unlike the schemes based on Large Vocabulary Continuous Speech Recognition (LVCSR) with previously trained phone models, our systems are based on units derived in unsupervised manner using the ALISP (Automatic Language Independent Processing) tools. Speaker modeling is then done independently for each class of speech sounds. Among the techniques to merge the class-dependent scores, linear combination was tested and logistic regression and a method based on the Mixture of Experts technique are under investigation. The experimental results were obtained on the data from the NIST-NSA'98 campaign.

langue originale	Anglais
titre	Proceedings of the 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Pages	2207-2210
Nombre de pages	4
état	Publié - 1999
Evénement	6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 - Budapest, Hongrie Durée: 5 sept. 1999 → 9 sept. 1999

Une conférence

Une conférence	6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Pays/Territoire	Hongrie
La ville	Budapest
période	5/09/99 → 9/09/99

Autres fichiers et liens

Lien vers la publication sur Scopus

Contient cette citation

@inproceedings{230fed104f444b38b2e6c882e609a3ef,

title = "A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION",

abstract = "Current text-independent speaker verification systems are usually based on modeling globally the probability density function (PDF) of the speaker feature vectors. In this paper, segmental approaches to text-independent speaker verification are discussed. Unlike the schemes based on Large Vocabulary Continuous Speech Recognition (LVCSR) with previously trained phone models, our systems are based on units derived in unsupervised manner using the ALISP (Automatic Language Independent Processing) tools. Speaker modeling is then done independently for each class of speech sounds. Among the techniques to merge the class-dependent scores, linear combination was tested and logistic regression and a method based on the Mixture of Experts technique are under investigation. The experimental results were obtained on the data from the NIST-NSA'98 campaign.",

keywords = "data fusion, segmental approach, text-independent speaker verification",

author = "J. {\v C}ernock{\'y} and D. Petrovska-Delacr{\'e}taz and S. Pigeon and Patrick Verlinde and G. Chollet",

note = "Publisher Copyright: {\textcopyright} 1999 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. All rights reserved.; 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 ; Conference date: 05-09-1999 Through 09-09-1999",

year = "1999",

language = "English",

pages = "2207--2210",

booktitle = "Proceedings of the 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999",

}

Černocký, J, Petrovska-Delacrétaz, D, Pigeon, S, Verlinde, P & Chollet, G 1999, A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION. Dans Proceedings of the 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. p. 2207-2210, 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999, Budapest, Hongrie, 5/09/99.

A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION. / Černocký, J.; Petrovska-Delacrétaz, D.; Pigeon, S. et al.
Proceedings of the 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. 1999. p. 2207-2210.

Résultats de recherche: Chapitre dans un livre, un rapport, des actes de conférences › Contribution à une conférence › Revue par des pairs

TY - GEN

T1 - A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION

AU - Černocký, J.

AU - Petrovska-Delacrétaz, D.

AU - Pigeon, S.

AU - Verlinde, Patrick

AU - Chollet, G.

PY - 1999

Y1 - 1999

N2 - Current text-independent speaker verification systems are usually based on modeling globally the probability density function (PDF) of the speaker feature vectors. In this paper, segmental approaches to text-independent speaker verification are discussed. Unlike the schemes based on Large Vocabulary Continuous Speech Recognition (LVCSR) with previously trained phone models, our systems are based on units derived in unsupervised manner using the ALISP (Automatic Language Independent Processing) tools. Speaker modeling is then done independently for each class of speech sounds. Among the techniques to merge the class-dependent scores, linear combination was tested and logistic regression and a method based on the Mixture of Experts technique are under investigation. The experimental results were obtained on the data from the NIST-NSA'98 campaign.

AB - Current text-independent speaker verification systems are usually based on modeling globally the probability density function (PDF) of the speaker feature vectors. In this paper, segmental approaches to text-independent speaker verification are discussed. Unlike the schemes based on Large Vocabulary Continuous Speech Recognition (LVCSR) with previously trained phone models, our systems are based on units derived in unsupervised manner using the ALISP (Automatic Language Independent Processing) tools. Speaker modeling is then done independently for each class of speech sounds. Among the techniques to merge the class-dependent scores, linear combination was tested and logistic regression and a method based on the Mixture of Experts technique are under investigation. The experimental results were obtained on the data from the NIST-NSA'98 campaign.

KW - data fusion

KW - segmental approach

KW - text-independent speaker verification

UR - http://www.scopus.com/inward/record.url?scp=34147191768&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34147191768

SP - 2207

EP - 2210

BT - Proceedings of the 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

T2 - 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Y2 - 5 September 1999 through 9 September 1999

ER -

A SEGMENTAL APPROACH TO TEXT-INDEPENDENT SPEAKER VERIFICATION

Résumé

Une conférence

Autres fichiers et liens

Empreinte digitale

Contient cette citation