Discriminative training of Gaussian mixture bigram models with application to Chinese dialect identification

W. H. Tsai, Wen-Whei Chang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

This study focuses on the parametric stochastic modeling of characteristic sound features that distinguish languages from one another. A new stochastic model, the so-called Gaussian mixture bigram model (GMBM), that allows exploitation of the acoustic feature bigram statistics without requiring transcribed training data is introduced. For greater efficiency, a minimum classification error (MCE) algorithm is employed to accomplish discriminative training of a GMBM-based Chinese dialect identification system. Simulation results demonstrate the effectiveness of the GMBM for dialect-specific acoustic modeling, and use of this model allows the proposed system to distinguish between the three major Chinese dialects spoken in Taiwan with 94.4% accuracy.

Original languageEnglish
Pages (from-to)317-326
Number of pages10
JournalSpeech Communication
Volume36
Issue number3-4
DOIs
StatePublished - 1 Mar 2002

Keywords

  • Chinese dialect identification
  • Gaussian mixture bigram model
  • Minimum classification error algorithm

Fingerprint Dive into the research topics of 'Discriminative training of Gaussian mixture bigram models with application to Chinese dialect identification'. Together they form a unique fingerprint.

Cite this