Speaker adaptation through canonical correlation analysis

The classification of phonemes, issued from a distance measure based on the linear prediction residuals is investigated, focusing on the dependency of the scores (of good recognition) upon the identity of the speaker. Starting from templates well adapted to the voice of one (standard) speaker, a scheme is proposed in order to improve the templates accordingly to global properties of the voice of the new speaker. The required transformation is linear and obtained by means of the statistical tool of canonical correlation analysis. Experiments carried out over six speakers show the adequacy of this transformation.