论文信息 - Phonological modeling for continuous speech recognition in Korean

Phonological modeling for continuous speech recognition in Korean

A new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the conditions of Korean phonological changes. A pairwise language model of these morphological and phonological tags is implemented in Korean speech recognition system. Performance of the model is verified through the TDNN-based speech recognition experiments.

[1] Keh-Jiann Chen,et al. An intelligent and efficient word-class-based Chinese language model for Mandarin speech recognition with very large vocabulary , 1994, ICSLP.

[2] Pascale Fung,et al. The BBN/HARC spoken language understanding system , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3] Masaaki Nagata. A stochastic morphological analyzer for spontaneously spoken languages , 1994, ICSLP.

[4] Michèle Jardino. A class bigram model for very large corpus , 1994, ICSLP.

[5] Kai-Fu Lee,et al. Automatic Speech Recognition , 1989 .