Detail publikace
Discriminatively Trained i-vector Extractor for Speaker Verification
GLEMBEK, O. BURGET, L. BRÜMMER, N. PLCHOT, O. MATĚJKA, P.
Originální název
Discriminatively Trained i-vector Extractor for Speaker Verification
Anglický název
Discriminatively Trained i-vector Extractor for Speaker Verification
Jazyk
en
Originální abstrakt
We have proposed a technique for discriminative training of the i-vector extractor parameters using cross-entropy as the error function. We have applied the technique both to the original i-vector extractor and to its simplified version. In both cases, the discriminative training was effective, giving higher relative improvement in the simplified case.
Anglický abstrakt
We have proposed a technique for discriminative training of the i-vector extractor parameters using cross-entropy as the error function. We have applied the technique both to the original i-vector extractor and to its simplified version. In both cases, the discriminative training was effective, giving higher relative improvement in the simplified case.
Dokumenty
BibTex
@inproceedings{BUT76447,
author="Ondřej {Glembek} and Lukáš {Burget} and Niko {Brümmer} and Oldřich {Plchot} and Pavel {Matějka}",
title="Discriminatively Trained i-vector Extractor for Speaker Verification",
annote="We have proposed a technique for discriminative training of the i-vector
extractor parameters using cross-entropy as the error function. We have applied
the technique both to the original i-vector extractor and to its simplified
version. In both cases, the discriminative training was effective, giving higher
relative improvement in the simplified case.",
address="International Speech Communication Association",
booktitle="Proceedings of Interspeech 2011",
chapter="76447",
edition="NEUVEDEN",
howpublished="print",
institution="International Speech Communication Association",
number="8",
year="2011",
month="august",
pages="137--140",
publisher="International Speech Communication Association",
type="conference paper"
}