Smoothing Method for Improved Minimum Phone Error Linear Regression

Yaohui QI  Fuping PAN  Fengpei GE  Qingwei ZHAO  Yonghong YAN  

IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.8   pp.2105-2113
Publication Date: 2014/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E97.D.2105
Type of Manuscript: PAPER
Category: Speech and Hearing
speaker adaptation (SA),  maximum likelihood linear regression (MLLR),  maximum a posteriori linear regression (MAPLR),  minimum phone error linear regression (MPELR),  discriminative maximum a posteriori linear regression (DMAPLR),  

Full Text: PDF(789.4KB)>>
Buy this Article

A smoothing method for minimum phone error linear regression (MPELR) is proposed in this paper. We show that the objective function for minimum phone error (MPE) can be combined with a prior mean distribution. When the prior mean distribution is based on maximum likelihood (ML) estimates, the proposed method is the same as the previous smoothing technique for MPELR. Instead of ML estimates, maximum a posteriori (MAP) parameter estimate is used to define the mode of prior mean distribution to improve the performance of MPELR. Experiments on a large vocabulary speech recognition task show that the proposed method can obtain 8.4% relative reduction in word error rate when the amount of data is limited, while retaining the same asymptotic performance as conventional MPELR. When compared with discriminative maximum a posteriori linear regression (DMAPLR), the proposed method shows improvement except for the case of limited adaptation data for supervised adaptation.