5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Automatic Recognition of Korean Broadcast News Speech

Ha-Jin Yu (1), Hoon Kim (1), Jae-Seung Choi (1), Joon-Mo Hong (2), Kew-Suh Park (2), Jong-Seok Lee (2), Hee-Youn Lee (2)

(1) LG Corporate Institute Of Technology, Korea
(2) LG Corporate Institute of Technology, Korea

This paper describes preliminary results of automatic recognition of Korean broadcast-news speech. We have been working on flexible vocabulary isolated-word speech recognition, and the same HMM models are used for broadcast-news continuous speech recognition. The recognizer is trained by using phonetically balanced isolated words speech, rather than the broadcast news speech itself. In this research, we use several different lexica to investigate the recognition performance according to the length of the words. We also propose a long-distance bigram language model, which can be used at the first stage of the search, so that it can reduce the recognition errors caused by earlier pruning of correct hypothesis.

Full Paper

Bibliographic reference.  Yu, Ha-Jin / Kim, Hoon / Choi, Jae-Seung / Hong, Joon-Mo / Park, Kew-Suh / Lee, Jong-Seok / Lee, Hee-Youn (1998): "Automatic recognition of Korean broadcast news speech", In ICSLP-1998, paper 0412.