Acoustic-labial speaker verification

Pierre Jourlin 1 D Genoud H Wassner
1 LIA - Laboratoire Informatique d'Avignon
Abstract : This paper describes a multimodal approach for speaker verification. The system consists of two classifiers, one using visual features, the other using acoustic features. A lip tracker is used to extract visual information from the speaking face which provides shape and intensity features. We describe an approach for normalizing and mapping different modalities onto a common confidence interval. We also describe a novel method for integrating the scores of multiple classifiers. Verification experiments are reported for the individual modalities and for the combined classifier. The integrated system outperformed each subsystem and reduced the false acceptance rate of the acoustic subsystem from 2.3% to 0.5%. © 1997 Elsevier Science B.V.
Keywords : Bimodal speech Person authentication Hidden Markov models Lip feature extraction Decision fusion
Document type :
Journal articles
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download
https://hal-univ-avignon.archives-ouvertes.fr/hal-02152874
Contributor : Pierre Jourlin <>
Submitted on : Thursday, June 13, 2019 - 12:06:55 PM
Last modification on : Tuesday, January 14, 2020 - 10:38:07 AM

File

prl97.pdf
Publisher files allowed on an open archive

Licence

Copyright

Identifiers

  • HAL Id : hal-02152874, version 1

Collections

UNIV-AVIGNON | LIA

Citation

Pierre Jourlin, D Genoud, H Wassner. Acoustic-labial speaker verification. Pattern Recognition Letters, Elsevier, 1997, 18, pp.853 - 858. ⟨hal-02152874⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

21

Files downloads

51

Contact

Informations

CCSD