Skip to Main content Skip to Navigation
Conference papers

MODELLING THE ALTERNATIVE HYPOTHESIS FOR TEXT-DEPENDENT SPEAKER VERIFICATION

Abstract : This paper describes text-dependent speaker verification as a task involving four classes of trials depending on whether the target speaker or an impostor pronounces the expected pass-phrase or not. These four classes are used to reformulate the log-likelihood ratio traditionally used in text-independent speaker verification. Three formulations of the alternative hypothesis are considered, leading to three new expressions of the verification score. Experiments performed on the publicly available RSR2015 database show a significant improvement compared to existing baseline scores. A relative gain up to 61% in term of minimum cost is achieved when considering that the alternative hypothesis is the union of three sub-hypotheses corresponding to the three existing classes of impostures.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01927571
Contributor : Anthony Larcher <>
Submitted on : Monday, November 19, 2018 - 11:23:21 PM
Last modification on : Monday, March 9, 2020 - 10:38:17 AM
Document(s) archivé(s) le : Wednesday, February 20, 2019 - 4:16:06 PM

File

Modelling_the_alternative_hypo...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01927571, version 1

Collections

Citation

Anthony Larcher, Koing Aik Lee, Bin Ma, Haizhou Li. MODELLING THE ALTERNATIVE HYPOTHESIS FOR TEXT-DEPENDENT SPEAKER VERIFICATION. IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP), May 2014, Florence, Italy. ⟨hal-01927571⟩

Share

Metrics

Record views

70

Files downloads

119