INTERSPEECH 2007 8th Annual Conference of the International Speech Communication Association Antwerp, Belgium August 27-31, 2007

Advances in Mandarin Broadcast Speech Recognition

Mei-Yuh Hwang (1), Wen Wang (2), Xin Lei (1), Jing Zheng (2), Ozgur Cetin (3), Gang Peng (1)

(1) University of Washington, USA
(2) SRI International, USA
(3) ICSI, USA

We describe our continuing efforts to improve the UW-SRI-ICSI Mandarin broadcast speech recognizer. This includes increasing acoustic and text training data, adding discriminative features, incorporating frame-level discriminative training criterion, multiple-pass acoustic model (AM) cross adaptation, language model (LM) genre adaptation and system combination. The net effect without LM adaptation was a 24%-64% relative reduction in character error rates (CERs) on a variety of test sets. In addition, LM adaptation gave us another 6% of relative CER reduction on broadcast conversations.

Full Paper

Bibliographic reference.  Hwang, Mei-Yuh / Wang, Wen / Lei, Xin / Zheng, Jing / Cetin, Ozgur / Peng, Gang (2007): "Advances in Mandarin broadcast speech recognition", In INTERSPEECH-2007, 2613-2616.