Advances in Mandarin broadcast speech recognition

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, multiplepass 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.