Fast speaker adaptation using eigenspace-based maximum likelihood linear regression

Abstract

This paper presents an eigenspace-based fast speaker adaptation approach which can improve the modeling accuracy of the conventional maximum likelihood linear regression (MLLR) techniques when only very limited adaptation data is available. The proposed eigenspace-based MLLR approach was developed by introducing a priori knowledge analysis on the training speakers via PCA, so as to construct an eigenspace for MLLR full regression matrices as well as to derive a set of bases called eigen-matrices. The full regression matrices for each outside speaker are then constrained to be located in the space spanned by the first K eigen-matrices. The proposed eigenspace-based regression matrices, serving as an initial estimate of the speaker-specific MLLR transformation, effectively reduces the number of free parameters, while precise modeling for the inter-dimensional correlation among the model parameters by full matrices was maintained. Experimental results showed that for supervised adaptation using adaptation data with a length of approximately 10 seconds, the proposed approach significantly outperformed the conventional MLLR approaches.