Detail publikace
A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix
RATH, S. BURGET, L. KARAFIÁT, M. GLEMBEK, O. ČERNOCKÝ, J.
Originální název
A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix
Typ
článek ve sborníku mimo WoS a Scopus
Jazyk
angličtina
Originální abstrakt
This paper describes the difficulties associated with soft R-FMLLR. By analyzing the Jacobian matrix, it was concludedthat the transformation is most likely to be non-invertibleand in this case ML estimation adversely affects the performance.A new transformation, hard R-FMLLR, is presented. Itis shown that the performance of the proposed method is betterthan soft R-FMLLR and it is computationally more efficient.
Klíčová slova
speaker recognition, speaker adaptation, feature-space transformation, speech recognition
Autoři
RATH, S.; BURGET, L.; KARAFIÁT, M.; GLEMBEK, O.; ČERNOCKÝ, J.
Rok RIV
2013
Vydáno
25. 8. 2013
Nakladatel
International Speech Communication Association
Místo
Lyon
ISBN
978-1-62993-443-3
Kniha
Proceedings of Interspeeech 2013
ISSN
2308-457X
Periodikum
Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).
Číslo
8
Stát
Francouzská republika
Strany od
1228
Strany do
1232
Strany počet
5
URL
BibTex
@inproceedings{BUT103551,
author="Shakti Prasad {Rath} and Lukáš {Burget} and Martin {Karafiát} and Ondřej {Glembek} and Jan {Černocký}",
title="A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix",
booktitle="Proceedings of Interspeeech 2013",
year="2013",
journal="Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).",
number="8",
pages="1228--1232",
publisher="International Speech Communication Association",
address="Lyon",
isbn="978-1-62993-443-3",
issn="2308-457X",
url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/rath_interspeech2013_IS130146.pdf"
}