Multifactor Adaptation for Mandarin Broadcast News and Conversation Speech Recognition

We explore the integration of multiple factors such as genre and speaker gender for acoustic model adaptation tasks to improve Mandarin ASR system performance on broadcast news and broadcast conversation audio. We investigate the use of mul-tifactor clustering of acoustic model training data and the ap-plication of MPE-MAP and fMPE-MAP acoustic model adap-tations. We found that by effectively combining these adapta-tion approaches, we achieve 6 % relative reduction in recogni-tion error rate compared to a Mandarin recognition system that does not use genre-specific acoustic models, and 5 % relative improvement if the genre-adaptive system is combined with an-other, genre-independent state-of-the-art system. Index Terms: large vocabulary automatic speech recognition, broadcast news, broadcast conversation, genre classification, MAP adaptation, MPE-MAP, fMPE-MAP 1