首页|Candidate Expansion Algorithm Based on Weighted Syllable Confusion Matrix for Mandarin LVCSR

Candidate Expansion Algorithm Based on Weighted Syllable Confusion Matrix for Mandarin LVCSR

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
The inclusion of more potentially correct words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition (LVCSR).A candidate expansion algorithm based on the Weighted Syllable Confusion Matrix (WSCM) is proposed.First,WSCM is derived from a confusion network.Then,the recognised candidates in the confusion network is used to conjecture the most likely correct words based on WSCM,after which,the conjectured words are combined with the recognised candidates to produce an expanded candidate set.Finally,a combined model having mutual information and a trigram language model is used to rerank the candidates.The experiments on Mandarin film data show that an improvement of 9.57％ in the character correction rate is obtained over the initial recognition performance on those light erroneous utterances.

speech recognitioncandidate expansionconfusion matrix

CHANG Fengxiang、LI Baoxiang、LIU Gang、GUO Jun

展开 >

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China

This study was supported by the National Natural Science Foundation of ChinaThis study was supported by the National Natural Science Foundation of ChinaThis study was supported by the National Natural Science Foundation of ChinaNext-Generation Broadband Wireless Mobile Communications Network Technology Key ProjectOne Church,One Family,One Purpose (111 Project)Key Project of Ministry of Science and Technology of ChinaNational High Technical Research and Development Program of China (863 Program)

6100500461175011611711932011ZX03002-005-01B080042012ZX-03002019-0022011A-A01A205

2013

中国通信(英文版)

中国通信(英文版)

CSTPCDCSCDSCI
影响因子：0.463
ISSN：1673-5447
年,卷(期)：2013.10(7)
  • 5