Continuous Speech Recognition Consortium — an Open Repository for CSR Tools and Models

Akinobu Lee (Nara Institute of Science and Technology Takayama-cho, Ikoma 630-0101, Japan)

Tatsuya Kawahara (Kyoto University Sakyo-ku, Kyoto 606-8501, Japan)

Kazuya Takeda (Nagoya University Chikusa-ku, Nagoya 464-8603, Japan)

Masato Mimura (Simogyo-ku, Kyoto 600-8813, Japan)

Atsushi Yamada (Simogyo-ku, Kyoto 600-8813, Japan)

Akinori Ito (Tohoku University Aoba-ku, Sendai 980-8577, Japan)

Katsunobu Itou (Agency of Industrial Science and Technology Umezono, Tsukuba 305-8568, Japan)

Kiyohiro Shikano (Nara Institute of Science and Technology Takayama-cho, Ikoma 630-0101, Japan)

SO7: Tools For Spoken LRs

Continuous Speech Recognition Consortium (CSRC) was founded on 2000 to promote sharable high-quality platform for research and development of speech recognition. It is a continued work of the former Japanese Dictation Toolkit project from 1997 to 2000. An overview of the software developed in the first year (Oct. 2000 - Sep. 2001) is given in this paper. We have revised the LVCSR (large vocabulary continuous speech recognition) engine Julius, and constructed new acoustic models using very large speech corpora. Moreover, a variety of acoustic and language models as well as tools are being set up. Currently over 50 companies and academic institutes are joining. The software is available by contacting the address csrc@astem.or.jp.

Speech recognition

339.pdf