Speaker recognition by separating phonetic space and speaker space

Abstract

In speaker recognition, it is a problem that speech f e ature varies depending on sentences and time di erence.This variation is mainly attributed to the variation of phonetic information and speaker information included in speech data.If these two kinds of information are separated each other, robust speaker recognition will be realized.In this study, w e propose a speaker identi cation and speaker veri cation method by separating the phonetic information and speaker information by a subspace method, under the assumption that a space with large within-speaker variance is a \phonetic space" and a space with small within-speaker variance is a \speaker space".We carried out comparative experiments of the proposed method with a conventional method based on GMM in an observation space as well as in a space transformed by L D A. As a result, we could construct a robust speaker model with a few model parameters using a few training data by the proposed method.