Unsupervised pronunciation grammar generation for non-native speech recognition

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

研究成果: Conference contribution

摘要

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.

原文English
主出版物標題TENCON 2007 - 2007 IEEE Region 10 Conference
DOIs
出版狀態Published - 2007 十二月 1
事件IEEE Region 10 Conference, TENCON 2007 - Taipei, Taiwan
持續時間: 2007 十月 302007 十一月 2

出版系列

名字IEEE Region 10 Annual International Conference, Proceedings/TENCON

Other

OtherIEEE Region 10 Conference, TENCON 2007
國家Taiwan
城市Taipei
期間07-10-3007-11-02

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

指紋 深入研究「Unsupervised pronunciation grammar generation for non-native speech recognition」主題。共同形成了獨特的指紋。

引用此