8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Mean and Covariance Adaptation Based on Minimum Classification Error Linear Regression for Continuous Density HMMs

Haibin Liu, Zhenyang Wu

Southeast University, China

The performance of speech recognition system will be significantly deteriorated because of the mismatches between training and testing conditions. This paper addresses the problem and proposes an algorithm to adapt the mean and covariance of HMM simultaneously within the minimum classification error linear regression (MCELR) framework. Rather than estimating the transformation parameters using maximum likelihood estimation (MLE) or maximum a posteriori, we proposed to use minimum classification error (MCE) as the estimation criterion. The proposed algorithm, called IMCELR (Improved MCELR), has been evaluated on a Chinese digit recognition tasks based on continuous density HMM. The experiments show that the proposed algorithm is more efficient than maximum likelihood linear regression with the same amount of adaptation data.

Full Paper

Bibliographic reference.  Liu, Haibin / Wu, Zhenyang (2004): "Mean and covariance adaptation based on minimum classification error linear regression for continuous density HMMs", In INTERSPEECH-2004, 2961-2964.