Journal of the Acoustical Society of Japan (E)
Online ISSN : 2185-3509
Print ISSN : 0388-2861
Japanese Dictation Toolkit-1997 version-
Tatsuya KawaharaAkinobu LeeTetsunori KobayashiKazuya TakedaNobuaki MinematsuKatsunobu ItouAkinori ItoMikio YamamotoAtsushi YamadaTakehito UtsuroKiyohiro Shikano
Author information

1999 Volume 20 Issue 3 Pages 233-239


The Japanese Dictation Toolkit has been designed and developed as a baseline platform for Japanese LVCSR (Large Vocabulary Continuous Speech Recognition). The platform consists of a standard recognition engine, Japanese phone models and Japanese statistical language models. We set up a variety of Japanese phone HMMs from a contextindependent monophone to a triphone model of thousands of states. They are trained with ASJ (The Acoustical Society of Japan) databases. A lexicon and word N-gram (2-gram and 3-gram) models are constructed with a corpus of Mainichi newspaper. The recognition engine JULIUS is developed for evaluation of both acoustic and language models. As an integrated system of these modules, we have implemented a baseline 5, 000-word dictation system and evaluated various components. The software repository is available to the public.

Information related to the author
© The Acoustical Society of Japan
Previous article Next article