Bayesian approaches in speech recognition

Shinji Watanabe*

*この研究の対応する著者

研究成果査読

抄録

This paper focuses on applications of Bayesian approaches to speech recognition. Bayesian approaches have been widely studied in statistics and machine learning fields, and one of the advantages of the Bayesian approaches is to improve generalization ability compared to maximum likelihood approaches. The effectiveness for speech recognition is shown experimentally in speaker adaptation tasks by using Maximum A Posterior (MAP) and model complexity control by using Bayesian Information Criterion (BIC). This paper introduces the variational Bayesian approaches, in addition to the MAP, BIC and other Bayesian techniques, for speech recognition. VBEC (Variational Bayesian Estimation and Clustering for speech recognition) is a fully Bayesian speech recognition framework, and achieves robust acoustic modeling and speech classification. This paper explains the formulation and experimental effectiveness of these Bayesian approaches for speech recognition.

本文言語English
ページ170-179
ページ数10
出版ステータスPublished - 2011 12 1
外部発表はい
イベントAsia-Pacific Signal and Information Processing Association Annual Summit and Conference 2011, APSIPA ASC 2011 - Xi'an, China
継続期間: 2011 10 182011 10 21

Conference

ConferenceAsia-Pacific Signal and Information Processing Association Annual Summit and Conference 2011, APSIPA ASC 2011
国/地域China
CityXi'an
Period11/10/1811/10/21

ASJC Scopus subject areas

  • 情報システム
  • 信号処理

フィンガープリント

「Bayesian approaches in speech recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル