We propose a method for automatically generating a pronunciation dictionary based on a pronunciation neural network that can predict plausible pronunciations (realized pronunciations) from canonical pronunciations. This method can generate multiple forms of realized pronunciations using the pronunciation network. Experimental results on spontaneous speech show that the automatically-derived pronunciation dictionary gives consistently higher recognition rates than a conventional dictionary.
Cite as: Fukada, T., Yoshimura, T., Sagisaka, Y. (1998) Neural network based pronunciation modeling with applications to speech recognition. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0658, doi: 10.21437/ICSLP.1998-399
@inproceedings{fukada98_icslp,
author={Toshiaki Fukada and Takayoshi Yoshimura and Yoshinori Sagisaka},
title={{Neural network based pronunciation modeling with applications to speech recognition}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0658},
doi={10.21437/ICSLP.1998-399}
}