Development of the 2008 SRI Mandarin speech-to-text system for broadcast news and conversation
Xin Lei, Wei Biao Wu, Wen Wang, Arindam Mandal, Andreas Stolcke · 2009
We describe the recent progress in SRI’s Mandarin speech-to-text system developed for 2008 evaluation in the DARPAGALE program. A data-driven lexicon expansion technique and lan-guage model adaptation methods contribute to the improvement in recognition performance. Our system yields 8.3 % character error rate on the GALE dev08 test set, and 7.5 % after combining with RWTH systems. Compared to our 2007 evaluation system, a significant improvement of 13 % relative has been achieved. Index Terms: lexicon expansion, language model adaptation, Mandarin speech recognition