The high error rate of recognition accuracy in spontaneous speech is due in part to the poor modeling of pronunciations. In this paper, we propose modeling pronunciation variations through triphone model reconstruction. We first generate partial change phone model (PCPM) to differentiate pronunciation variations. In order to improve the resolution of triphone models, PCPM is used as a hidden model and merged into the pre-trained acoustic model through model reconstruction. To avoid model confusion, auxiliary decision trees are established for triphone PCPMs. The acoustic model reconstruction on triphones is equivalent to decision tree merging. The effectiveness of this approach is evaluated on the 1997 Hub4NE Mandarin Broadcast News Corpus (1997 MBN) with different styles of speech. It gives a significant 2.39% absolute syllable error rate reduction in spontaneous speech.
展开▼
