Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Rapid Adaptation Of N-Gram Language Models Using Inter-Word Correlation for Speech Recognition

Koki Sasaki (1), Hui Jiang (2), Keikichi Hirose (1)

(1) Department of Information and Communication Engineering, University of Tokyo, Bunkyu-ku, Tokyo, Japan
(2) Dialog Systems Research, Multimedia Communication Research Lab, Bell Labs, Lucent Technologies, Murray Hill, NJ, USA

In this paper, we study the fast adaptation problem of n-gram language model under the MAP estimation framework. We have proposed a heuristic method to explore inter-word correlation to accelerate MAP adaptation of n-gram model. According to their correlations, the occurrence of one word can be used to predict all other words in adaptation text. In this way, a large n-gram model can be efficiently adapted with a small amount of adaptation data. The proposed fast adaptation approach is evaluated in a Japanese newspaper corpus. We have observed a significant perplexity reduction even when we have only several hundred adaptation sentences.

Full Paper

Bibliographic reference.  Sasaki, Koki / Jiang, Hui / Hirose, Keikichi (2000): "Rapid adaptation of n-gram language models using inter-word correlation for speech recognition", In ICSLP-2000, vol.4, 508-511.