Unsupervised pronunciation grammar generation for non-native speech recognition

Chien Lin Huang, Chung Hsien Wu, Yi Chen, Chin Shun Hsu, Kuei Ming Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This study presents a novel approach to unsupervised pronunciation grammar generation for non-native speech recognition. Unsupervised pronunciation grammar generation includes pronunciation variation graph construction, stochastic Markov search and grammar selection. Context-dependent relation and phone broad class information are used for variation graph construction. Confidence measure and co-occurrence frequency are used to select the variants of pronunciation grammar for non-native speech modeling. Experiments show that unsupervised pronunciation grammar generation is suitable for the improvement of non-native speech recognition.

Original languageEnglish
Title of host publicationTENCON 2007 - 2007 IEEE Region 10 Conference
Publication statusPublished - 2007 Dec 1
EventIEEE Region 10 Conference, TENCON 2007 - Taipei, Taiwan
Duration: 2007 Oct 302007 Nov 2

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON


OtherIEEE Region 10 Conference, TENCON 2007

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Unsupervised pronunciation grammar generation for non-native speech recognition'. Together they form a unique fingerprint.

Cite this