Automatic determination of acoustic model topology using variational Bayesian estimation and clustering

Shinji Watanabe, Atsushi Sako, Atsushi Nakamura

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

We describe the automatic determination of an acoustic model for speech recognition, which is very complicated and includes latent variables, using VBEC: Variational Bayesian Estimation and Clustering for speech recognition. We propose an efficient Gaussian Mixture Model (GMM) based phonetic decision tree construction within the VBEC framework. The proposed method features a novel approach to reduce the unrealistically large number of computations needed for iterative calculations in the GMM-based decision tree method to a practical level by assuming that each Gaussian per state has the same occupancy and is represented by the same posterior distribution for the covariance parameter. The experimental results confirmed that VBEC automatically provided a optimum model topology with the highest performance level.

Original languageEnglish
Pages (from-to)I813-I816
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
Publication statusPublished - 2004 Sep 28
Externally publishedYes
EventProceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Que, Canada
Duration: 2004 May 172004 May 21

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automatic determination of acoustic model topology using variational Bayesian estimation and clustering'. Together they form a unique fingerprint.

  • Cite this