Bayesian approaches to acoustic modeling: A review

Shinji Watanabe, Atsushi Nakamura

Research output: Contribution to journalArticle

Abstract

This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech-processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization capability is better than that of conventional approaches (e.g., maximum likelihood). On the other hand, since inference in Bayesian approaches involves integrals and expectations that are mathematically intractable in most cases and require heavy numerical computations, it is generally difficult to apply them to practical speech recognition problems. However, there have been many such attempts, and this paper aims to summarize these attempts to encourage further progress on Bayesian approaches in the speech-processing field. This paper describes various applications of Bayesian approaches to speech processing in terms of the four typical ways of approximating Bayesian inferences, i.e., maximum a posteriori approximation, model complexity control using a Bayesian information criterion based on asymptotic approximation, variational approximation, and Markov chain Monte Carlo-based sampling techniques.

Original languageEnglish
JournalJournal of Institutional Economics
Volume1
Issue number2
DOIs
Publication statusPublished - 2012 Aug 28
Externally publishedYes

Fingerprint

Bayesian approach
Modeling
Approximation
Speech recognition
Machine learning
Statistics
Inference
Integral
Markov chain Monte Carlo
Sampling
Bayesian inference
Bayesian information criterion
Maximum likelihood

Keywords

  • Approximate Bayesian inference
  • Bayesian approach
  • Machine learning
  • Speech processing

ASJC Scopus subject areas

  • Economics, Econometrics and Finance(all)

Cite this

Bayesian approaches to acoustic modeling : A review. / Watanabe, Shinji; Nakamura, Atsushi.

In: Journal of Institutional Economics, Vol. 1, No. 2, 28.08.2012.

Research output: Contribution to journalArticle

@article{faa4b40d51ae45249ab715c0a313c293,
title = "Bayesian approaches to acoustic modeling: A review",
abstract = "This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech-processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization capability is better than that of conventional approaches (e.g., maximum likelihood). On the other hand, since inference in Bayesian approaches involves integrals and expectations that are mathematically intractable in most cases and require heavy numerical computations, it is generally difficult to apply them to practical speech recognition problems. However, there have been many such attempts, and this paper aims to summarize these attempts to encourage further progress on Bayesian approaches in the speech-processing field. This paper describes various applications of Bayesian approaches to speech processing in terms of the four typical ways of approximating Bayesian inferences, i.e., maximum a posteriori approximation, model complexity control using a Bayesian information criterion based on asymptotic approximation, variational approximation, and Markov chain Monte Carlo-based sampling techniques.",
keywords = "Approximate Bayesian inference, Bayesian approach, Machine learning, Speech processing",
author = "Shinji Watanabe and Atsushi Nakamura",
year = "2012",
month = "8",
day = "28",
doi = "10.1017/ATSIP.2012.6",
language = "English",
volume = "1",
journal = "Journal of Institutional Economics",
issn = "1744-1374",
publisher = "Cambridge University Press",
number = "2",

}

TY - JOUR

T1 - Bayesian approaches to acoustic modeling

T2 - A review

AU - Watanabe, Shinji

AU - Nakamura, Atsushi

PY - 2012/8/28

Y1 - 2012/8/28

N2 - This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech-processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization capability is better than that of conventional approaches (e.g., maximum likelihood). On the other hand, since inference in Bayesian approaches involves integrals and expectations that are mathematically intractable in most cases and require heavy numerical computations, it is generally difficult to apply them to practical speech recognition problems. However, there have been many such attempts, and this paper aims to summarize these attempts to encourage further progress on Bayesian approaches in the speech-processing field. This paper describes various applications of Bayesian approaches to speech processing in terms of the four typical ways of approximating Bayesian inferences, i.e., maximum a posteriori approximation, model complexity control using a Bayesian information criterion based on asymptotic approximation, variational approximation, and Markov chain Monte Carlo-based sampling techniques.

AB - This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech-processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization capability is better than that of conventional approaches (e.g., maximum likelihood). On the other hand, since inference in Bayesian approaches involves integrals and expectations that are mathematically intractable in most cases and require heavy numerical computations, it is generally difficult to apply them to practical speech recognition problems. However, there have been many such attempts, and this paper aims to summarize these attempts to encourage further progress on Bayesian approaches in the speech-processing field. This paper describes various applications of Bayesian approaches to speech processing in terms of the four typical ways of approximating Bayesian inferences, i.e., maximum a posteriori approximation, model complexity control using a Bayesian information criterion based on asymptotic approximation, variational approximation, and Markov chain Monte Carlo-based sampling techniques.

KW - Approximate Bayesian inference

KW - Bayesian approach

KW - Machine learning

KW - Speech processing

UR - http://www.scopus.com/inward/record.url?scp=84915791644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84915791644&partnerID=8YFLogxK

U2 - 10.1017/ATSIP.2012.6

DO - 10.1017/ATSIP.2012.6

M3 - Article

AN - SCOPUS:84915791644

VL - 1

JO - Journal of Institutional Economics

JF - Journal of Institutional Economics

SN - 1744-1374

IS - 2

ER -