Unsupervised pronunciation grammar generation for non-native speech recognition

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.

[1]  F. Wolfertstetter,et al.  Structured Markov models for speech recognition , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[2]  Helmer Strik,et al.  Improving the performance of a Dutch CSR by modeling pronunciation variation , 1998 .

[3]  Xavier L. Aubert,et al.  Improved acoustic-phonetic modeling in philips' dictation system by handling liaisons and multiple pronunciations , 1995, EUROSPEECH.

[4]  Frank K. Soong,et al.  Generalized posterior probability for minimum error verification of recognized sentences , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[5]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[6]  Noam Chomsky,et al.  The Sound Pattern of English , 1968 .

[7]  Chung-Hsien Wu,et al.  Phone Set Generation Based on Acoustic and Contextual Analysis for Multilingual Speech Recognition , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[8]  F. Almasganj,et al.  A hybrid statistical model to generate pronunciation variants of words , 2005, 2005 International Conference on Natural Language Processing and Knowledge Engineering.