ISCA Archive - Neural network based pronunciation modeling with applications to speech recognition
ISCA Archive ICSLP 1998
ISCA Archive ICSLP 1998

Neural network based pronunciation modeling with applications to speech recognition

Toshiaki Fukada, Takayoshi Yoshimura, Yoshinori Sagisaka

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.