Přejít na obsah

Detail publikace

Citace

Jan Vaněk and Zbyněk Zajíc : A Direct Criterion Minimization based fMLLR via Gradient Descend . Text, Speech, and Dialogue, Lecture Notes in Computer Science, vol. 8082, p. 52-59, Springer, 2013.

PDF ke stažení

PDF

Abstrakt

Adaptation techniques are necessary in automatic speech recognizers to improve a recognition accuracy. Linear Transformation methods (MLLR or fMLLR) are the most favorite in the case of limited available data. The fMLLR is the feature-space transformation. This is the advantage with contrast to MLLR that transforms the entire acoustic model. The classical fMLLR estimation involves maximization of the likelihood criterion based on individual Gaussian components statistic. We proposed an approach which takes into account the overall likelihood of a HMM state. It estimates the transformation to optimize the ML criterion of HMM directly using gradient descent algorithm.

Abstrakt v češtině

Adaptation techniques are necessary in automatic speech recognizers to improve a recognition accuracy. Linear Transformation methods (MLLR or fMLLR) are the most favorite in the case of limited available data. The fMLLR is the feature-space transformation. This is the advantage with contrast to MLLR that transforms the entire acoustic model. The classical fMLLR estimation involves maximization of the likelihood criterion based on individual Gaussian components statistic. We proposed an approach which takes into account the overall likelihood of a HMM state. It estimates the transformation to optimize the ML criterion of HMM directly using gradient descent algorithm.

Detail publikace

Název: A Direct Criterion Minimization based fMLLR via Gradient Descend
Autor: Jan Vaněk ; Zbyněk Zajíc
Název - česky: A Direct Criterion Minimization based fMLLR via Gradient Descend
Jazyk publikace: anglicky
Datum vydání: 1.9.2013
Rok vydání: 2013
Typ publikace: Stať ve sborníku
Název knihy: Text, Speech, and Dialogue
Svazek: Lecture Notes in Computer Science
Číslo vydání: 8082
Strana: 52 - 59
DOI: 10.1007/978-3-642-40585-3_8
ISBN: 978-3-642-40584-6
Nakladatel: Springer
/ 2014-11-12 12:21:25 /

Klíčová slova

ASR, adaptation, fMLLR, gradient descend, Hessian matrix

Klíčová slova v češtině

ASR, adaptation, fMLLR, gradient descend, Hessian matrix

BibTeX

@INPROCEEDINGS{JanVanek_2013_ADirectCriterion,
 author = {Jan Van\v{e}k and Zbyn\v{e}k Zaj\'{i}c},
 title = {A Direct Criterion Minimization based fMLLR via Gradient Descend},
 year = {2013},
 publisher = {Springer},
 volume = {8082},
 pages = {52-59},
 booktitle = {Text, Speech, and Dialogue},
 series = {Lecture Notes in Computer Science},
 ISBN = {978-3-642-40584-6},
 doi = {10.1007/978-3-642-40585-3_8},
 url = {http://www.kky.zcu.cz/en/publications/JanVanek_2013_ADirectCriterion},
}