Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

Recent Advances in Japanese Broadcast News Transcription

Katsutoshi Ohtsuki (1), Sadaoki Furui (2), Naoyuki Sakurai (2), Atsushi Iwasaki (2), Zhi-Peng Zhang (2)

(1) NTT Cyber Space Laboratories, Media Processing Project, Yokosuka-shi, Kanagawa, Japan
(2) Tokyo Institute of Technology, Department of Computer Science, Meguro-ku, Tokyo, Japan

In this paper, we report on language modeling and acoustic modeling studies for Japanese broadcast news speech recognition. We constructed a language model that reduces recognition errors by utilizing context-dependent readings of Japanese characters. We also introduced filled-pause modeling into the language model. To improve the modelís performance for a series of sentences spoken by one speaker, an on-line incremental speaker adaptation was combined with automatic detection of speaker changes. By incorporating all the above methods, we achieved a 25.1% reduction in word error rate over the baseline results. This paper also reports on our preliminary studies on topic extraction and summarization of broadcast-news speech.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Ohtsuki, Katsutoshi / Furui, Sadaoki / Sakurai, Naoyuki / Iwasaki, Atsushi / Zhang, Zhi-Peng (1999): "Recent advances in Japanese broadcast news transcription", In EUROSPEECH'99, 671-674.