Discriminative Pronunciation Modeling Using the MPE Criterion

Meixu SONG  Jielin PAN  Qingwei ZHAO  Yonghong YAN  

IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.3   pp.717-720
Publication Date: 2015/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2014EDL8212
Type of Manuscript: LETTER
Category: Speech and Hearing
automatic speech recognition,  pronunciation models,  discriminative training,  Mandarin conversational speech recognition,  

Full Text: PDF>>
Buy this Article

Introducing pronunciation models into decoding has been proven to be benefit to LVCSR. In this paper, a discriminative pronunciation modeling method is presented, within the framework of the Minimum Phone Error (MPE) training for HMM/GMM. In order to bring the pronunciation models into the MPE training, the auxiliary function is rewritten at word level and decomposes into two parts. One is for co-training the acoustic models, and the other is for discriminatively training the pronunciation models. On Mandarin conversational telephone speech recognition task, compared to the baseline using a canonical lexicon, the discriminative pronunciation models reduced the absolute Character Error Rate (CER) by 0.7% on LDC test set, and with the acoustic model co-training, 0.8% additional CER decrease had been achieved.