Application of variational Bayesian estimation and clustering to acoustic model adaptation

Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, Naonori Ueda

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we apply Variational Bayesian Estimation and Clustering for speech recognition (VBEC) to an acoustic model adaptation. VBEC can estimate parameter posteriors even when a model includes hidden variables, by using Variational Bayesian approach. In addition, VBEC can select an appropriate model structure in clustering triphone states, according to the amount of available adaptation data. Unlike a conventional Bayesian method such as Maximum A Posteriori (MAP), VBEC is useful even in the case of small amounts of data, because the amount of data per one Gaussian increases due to the model structure selection, and over-training is suppressed. We conduct an off-line supervised adaptation experiment on isolated word recognition, and show the advantage of the proposed method over the conventional method, especially when dealing with small amounts of adaptation data.

Original languageEnglish
Pages (from-to)568-571
Number of pages4
JournalUnknown Journal
Volume1
Publication statusPublished - 2003
Externally publishedYes

Fingerprint

Model structures
Acoustics
acoustics
Speech recognition
speech recognition
education
Experiments
estimates

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Acoustics and Ultrasonics

Cite this

Application of variational Bayesian estimation and clustering to acoustic model adaptation. / Watanabe, Shinji; Minami, Yasuhiro; Nakamura, Atsushi; Ueda, Naonori.

In: Unknown Journal, Vol. 1, 2003, p. 568-571.

Research output: Contribution to journalArticle

Watanabe, Shinji ; Minami, Yasuhiro ; Nakamura, Atsushi ; Ueda, Naonori. / Application of variational Bayesian estimation and clustering to acoustic model adaptation. In: Unknown Journal. 2003 ; Vol. 1. pp. 568-571.
@article{116b077ed6d540e0be92eb541ad94fe2,
title = "Application of variational Bayesian estimation and clustering to acoustic model adaptation",
abstract = "In this paper, we apply Variational Bayesian Estimation and Clustering for speech recognition (VBEC) to an acoustic model adaptation. VBEC can estimate parameter posteriors even when a model includes hidden variables, by using Variational Bayesian approach. In addition, VBEC can select an appropriate model structure in clustering triphone states, according to the amount of available adaptation data. Unlike a conventional Bayesian method such as Maximum A Posteriori (MAP), VBEC is useful even in the case of small amounts of data, because the amount of data per one Gaussian increases due to the model structure selection, and over-training is suppressed. We conduct an off-line supervised adaptation experiment on isolated word recognition, and show the advantage of the proposed method over the conventional method, especially when dealing with small amounts of adaptation data.",
author = "Shinji Watanabe and Yasuhiro Minami and Atsushi Nakamura and Naonori Ueda",
year = "2003",
language = "English",
volume = "1",
pages = "568--571",
journal = "Nuclear Physics A",
issn = "0375-9474",
publisher = "Elsevier",

}

TY - JOUR

T1 - Application of variational Bayesian estimation and clustering to acoustic model adaptation

AU - Watanabe, Shinji

AU - Minami, Yasuhiro

AU - Nakamura, Atsushi

AU - Ueda, Naonori

PY - 2003

Y1 - 2003

N2 - In this paper, we apply Variational Bayesian Estimation and Clustering for speech recognition (VBEC) to an acoustic model adaptation. VBEC can estimate parameter posteriors even when a model includes hidden variables, by using Variational Bayesian approach. In addition, VBEC can select an appropriate model structure in clustering triphone states, according to the amount of available adaptation data. Unlike a conventional Bayesian method such as Maximum A Posteriori (MAP), VBEC is useful even in the case of small amounts of data, because the amount of data per one Gaussian increases due to the model structure selection, and over-training is suppressed. We conduct an off-line supervised adaptation experiment on isolated word recognition, and show the advantage of the proposed method over the conventional method, especially when dealing with small amounts of adaptation data.

AB - In this paper, we apply Variational Bayesian Estimation and Clustering for speech recognition (VBEC) to an acoustic model adaptation. VBEC can estimate parameter posteriors even when a model includes hidden variables, by using Variational Bayesian approach. In addition, VBEC can select an appropriate model structure in clustering triphone states, according to the amount of available adaptation data. Unlike a conventional Bayesian method such as Maximum A Posteriori (MAP), VBEC is useful even in the case of small amounts of data, because the amount of data per one Gaussian increases due to the model structure selection, and over-training is suppressed. We conduct an off-line supervised adaptation experiment on isolated word recognition, and show the advantage of the proposed method over the conventional method, especially when dealing with small amounts of adaptation data.

UR - http://www.scopus.com/inward/record.url?scp=0141591454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141591454&partnerID=8YFLogxK

M3 - Article

VL - 1

SP - 568

EP - 571

JO - Nuclear Physics A

JF - Nuclear Physics A

SN - 0375-9474

ER -