Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Effective Lexical Tree Search for Large Vocabulary Continuous Speech Recognition

Hiroki Yamamoto, Toshiaki Fukada, Yasuhiro Komori

Platform Technology Development Center, Canon Inc., Nakahara-ku, Kawasaki-shi, Kanagawa, Japan

In this paper, we present an ecient calculation of the factored LM probabilities for speeding up the large vocabulary continuous speech recognition. We introduced a novel technique based on the independent calculation of the factored LM probability. The basic idea of the proposed method is that each factored LM probability is calculated on-demand for a new combination of a previous word hypothesis and a LM look-ahead tree node, instead of calculating all the factored LM probabilities over the tree at a time. The speaker-independent continuous speech recognition experiment was performed for 20 speakers on a 60k word newspaper dictation task. As a result, the proposed method achieved 25% improvement in speed.

Full Paper

Bibliographic reference.  Yamamoto, Hiroki / Fukada, Toshiaki / Komori, Yasuhiro (2000): "Effective lexical tree search for large vocabulary continuous speech recognition", In ICSLP-2000, vol.4, 322-325.