Speaker recognition and speaker normalization by projection to speaker subspace

Abstract

An individual speaker is thought to have his own subspace in which his phonetic information is included. However, conventional speaker-independent HMMs ignore the speaker subspaces and gather speech data spread widely in the observation space. Then they cause probability distribution flatness of HMMs and the resultant recognition errors. To solve this problem, we propose a method (1) to separate the speaker characteristics by constructing the individual speaker subspace, (2) to recognize speakers based on the subspaces and (3) to produce speaker normalized speech data by projecting speech data into his subspace and to recognize them.