Effectiveness of speaker normalized HMM by projection to speaker subspace

Conventional speaker-independent HMMs ignore the speaker differences and collect speech data in an observation space. This causes a problem that probability distribution of the HMMs becomes flat, and then causes recognition errors. To solve this problem, we construct the speaker subspace for an individual speaker and project his speech data to his own subspace. By this method we can extract speaker independent phonetic information included in the speech data. Speaker-independent HMMs can be constructed using this phonetic information. In this paper, we describe the result of phoneme recognition experiments using the speaker-independent HMMs constructed by the speech data projected to the speaker subspaces