Application of variational Bayesian approach to speech recognition

Shinji Watanabe, Yasuhiro Minami, Atsushi Nakamura, Naonori Ueda

研究成果: Conference contribution

17 被引用数 (Scopus)

抄録

In this paper, we propose a Bayesian framework, which constructs shared-state triphone HMMs based on a variational Bayesian approach, and recognizes speech based on the Bayesian prediction classification; variational Bayesian estimation and clustering for speech recognition (VBEC). An appropriate model structure with high recognition performance can be found within a VBEC framework. Unlike conventional methods, including BIC or MDL criterion based on the maximum likelihood approach, the proposed model selection is valid in principle, even when there are insufficient amounts of data, because it does not use an asymptotic assumption. In isolated word recognition experiments, we show the advantage of VBEC over conventional methods, especially when dealing with small amounts of data.

本文言語English
ホスト出版物のタイトルAdvances in Neural Information Processing Systems 15 - Proceedings of the 2002 Conference, NIPS 2002
出版社Neural information processing systems foundation
ISBN(印刷版)0262025507, 9780262025508
出版ステータスPublished - 2003 1 1
外部発表はい
イベント16th Annual Neural Information Processing Systems Conference, NIPS 2002 - Vancouver, BC, Canada
継続期間: 2002 12 92002 12 14

出版物シリーズ

名前Advances in Neural Information Processing Systems
ISSN(印刷版)1049-5258

Other

Other16th Annual Neural Information Processing Systems Conference, NIPS 2002
CountryCanada
CityVancouver, BC
Period02/12/902/12/14

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

フィンガープリント 「Application of variational Bayesian approach to 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