INTERSPEECH 2004 - ICSLP
8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Recent Progress of Open-Source LVCSR Engine Julius and Japanese Model Repository

Tatsuya Kawahara (1), Akinobu Lee (2), Kazuya Takeda (3), Katsunobu Itou (3), Kiyohiro Shikano (2)

(1) Kyoto University, Japan
(2) Nara Institute of Science and Technology, Japan
(3) Nagoya University, Japan

Continuous Speech Recognition Consortium (CSRC) was founded for further enhancement of Japanese Dictation Toolkit that had been developed by the support of a Japanese agency. Overview of its product software is reported in this paper. The open-source LVCSR (large vocabulary continuous speech recognition) engine Julius has been improved both in performance and functionality, and it is also ported to Microsoft Windows in compliance with SAPI (Speech API). The software is now used for not a few languages and plenty of applications. For plug-and-play speech recognition in various applications, we have also compiled a repository of acoustic and language models for Japanese. Especially, the acoustic model set realizes wider coverage of user generations and speech-input environments.

Full Paper

Bibliographic reference.  Kawahara, Tatsuya / Lee, Akinobu / Takeda, Kazuya / Itou, Katsunobu / Shikano, Kiyohiro (2004): "Recent progress of open-source LVCSR engine julius and Japanese model repository", In INTERSPEECH-2004, 3069-3072.