Automatic determination of acoustic model topology using variational bayesian estimation and clustering for large vocabulary continuous speech recognition

Shinji Watanabe, Atsushi Sako, Atsushi Nakamura

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

We describe the automatic determination of a large and complicated acoustic model for speech recognition by using variational Bayesian estimation and clustering (VBEC) for speech recognition. We propose an efficient method for decision tree clustering based on a Gaussian mixture model (GMM) and an efficient model search algorithm for finding an appropriate acoustic model topology within the VBEC framework. GMM-based decision tree clustering for triphone HMM states features a novel approach designed to reduce the overly large number of computations to a practical level by utilizing the statistics of monophone hidden Markov model states. The model search algorithm also reduces the search space by utilizing the characteristics of the acoustic model. The experimental results confirmed that VBEC automatically and rapidly yielded an optimum model topology with the highest performance.

Original languageEnglish
Pages (from-to)855-872
Number of pages18
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume14
Issue number3
DOIs
Publication statusPublished - 2006 May 1
Externally publishedYes

Keywords

  • Determination of acoustic model topologies
  • Speech recognition
  • Variational bayes
  • Variational bayesian estimation and clustering (VBEC)

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automatic determination of acoustic model topology using variational bayesian estimation and clustering for large vocabulary continuous speech recognition'. Together they form a unique fingerprint.

  • Cite this