A new lexicon optimization method for LVCSR based on linguistic and acoustic characteristics of words

This paper proposes a new lexicon optimization method to improve recognition rate of large scale spontaneous speech recognition. Occurrence count and length of a word has strong correlation with difficulty of recognizing the word. First, we investigate the relation and make a word correctness probability model. The proposed method optimizes the lexicon by making compound words or phrases step by step based on the word correctness probability model so as to improve the estimated recognition rate of the system. The optimization method is applied to a large scale Japanese spontaneous speech corpus. Experimental results show that the language model using the optimized lexicon improves the recognition rate.

[1]  Egidio P. Giachin,et al.  Phrase bigrams for continuous speech recognition , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[2]  Alexander H. Waibel,et al.  Towards better language models for spontaneous speech , 1994, ICSLP.

[3]  Paolo Baggia,et al.  Language models for spontaneous speech recognition: a bootstrap method for learning phrase digrams , 1994, ICSLP.

[4]  Kyuwoong Hwang.  Vocabulary optimization based on perplexity , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Dietrich Klakow.  Language-model optimization by mapping of corpora , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[6]  Sadaoki Furui,et al.  Error analysis using decision trees in spontaneous presentation speech recognition , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[7]  Sadaoki Furui,et al.  Toward the realization of spontaneous speech recognition and summarization , 2000 .

[8]  Hong-Kwang Jeff Kuo,et al.  Phrase-based language models for speech recognition , 1999, EUROSPEECH.

[9]  Jianfeng Gao,et al.  Lexicon Optimization for Chinese Language Modeling , 2000 .