Adaptive HMM topology for speech recognition

Chuan Wei Ting*, Kuo Yuan Lee, Jen-Tzung Chien

*Corresponding author for this work

Research output: Contribution to journalConference article

2 Scopus citations

Abstract

This paper presents an adaptive algorithm for compensating pronunciation variations in hidden Markov model (HMM) based speech recognition. The proposed method aims to adapt the HMM topology and the corresponding HMM parameters to meet the variations of speaker dialects. In adaptive HMM topology, two hypothesis test schemes are designed to detect whether a new speaking variation occurs in state/phone levels. The test statistics are approximated by the chi-square densities. A new HMM topology is automatically generated by a significance level. Simultaneously, the HMM parameters and their hyperparameters are updated by Bayesian learning of the newly-generated Markov models. The pronunciation variations are coped with by a dialect adaptive HMM topology. We develop the incremental algorithm for corrective training of HMM topology and parameters. Experiments on TIMIT database show that the proposed algorithm is substantially better than the standard HMM with comparable size of parameters.

Original languageEnglish
Pages (from-to)1237-1240
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 1 Dec 2008
EventINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association - Brisbane, QLD, Australia
Duration: 22 Sep 200826 Sep 2008

Keywords

  • Bayesian learning
  • HMM topology
  • Hypothesis test
  • Pronunciation variation
  • Speech recognition

Fingerprint Dive into the research topics of 'Adaptive HMM topology for speech recognition'. Together they form a unique fingerprint.

Cite this