ISCA Archive SpeechProsody 2004
ISCA Archive SpeechProsody 2004

Duration modeling for Mandarin speech recognition using prosodic information

Wern-Jun Wang, Chun-Jen Lee

In this paper, a new duration modeling method for HMMbased Mandarin base-syllable recognition is proposed. It extends the conventional state duration method to further consider the speaking rate of utterance and add a syllable duration model to help the recognition search finding the bestrecognized base-syllable string. Experimental results showed that the proposed method was effective on improving the recognition accuracy.