The inclusion of more potentiallycorrect words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition(LVCSR).A candidate expansion algorithm based on theWeighted S...The inclusion of more potentiallycorrect words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition(LVCSR).A candidate expansion algorithm based on theWeighted Syllable Confusion Matrix(WSCM)is proposed.First,WSCM is derived from aconfusion network.Then,the recognised candidates in the confusion network is used to conjecture the most likely correct words based onWSCM,after which,the conjectured wordsare combined with the recognised candidatesto produce an expanded candidate set.Finally,a combined model having mutual informationand a trigram language model is used to rerank the candidates.The experiments on Mandarin film data show that an improvement of9.57% in the character correction rate is obtained over the initial recognition performanceon those light erroneous utterances.展开更多
基金supported by the National Natural Science Foundation of China under Grants No.61005004,No.61175011,No.61171193the Next-Generation Broadband Wireless Mobile Communications Network Technology Key Project under Grant No.2011ZX03002-005-01+2 种基金the One Church,One Family,One Purpose(111Project)under Grant No.B08004the Key Project of Ministry of Science and Technology of China under Grant No.2012ZX-03002019-002the National High Techni-cal Research and Development Program of China(863Program)under Grant No.2011A-A01A205
文摘The inclusion of more potentiallycorrect words in the candidate sets is important to improve the accuracy of Large Vocabulary Continuous Speech Recognition(LVCSR).A candidate expansion algorithm based on theWeighted Syllable Confusion Matrix(WSCM)is proposed.First,WSCM is derived from aconfusion network.Then,the recognised candidates in the confusion network is used to conjecture the most likely correct words based onWSCM,after which,the conjectured wordsare combined with the recognised candidatesto produce an expanded candidate set.Finally,a combined model having mutual informationand a trigram language model is used to rerank the candidates.The experiments on Mandarin film data show that an improvement of9.57% in the character correction rate is obtained over the initial recognition performanceon those light erroneous utterances.
