An approach to speaker adaptation based on analytic functions

We formulate a novel approach to speaker adaptation. It is predicated upon the fact that the cepstral coefficients used as feature vectors in most state of the art speech recognition systems are coefficients of a Laurent series, and hence represent an analytic function of a complex-valued argument. This analytic function can be characterized by several poles and zeros in the complex plane corresponding to spectral peaks and nulls, respectively. Speaker adaptation can be viewed as the estimation of a function that warps the complex plane in such a way that the pole/zero locations for a target speaker are mapped onto their counterparts in the speaker-independent model