Phonetic Subspace Mixture Model for Speaker Diarization

摘要

This paper presents an improved distance measure for speaker clustering in speaker diarization systems. The proposed phonetic subspace mixture (PSM) model introduces phonetic information to the ABIC distance measure. Therefore, the new PSM model-based ABIC distance measure can remove the effect of phonetic content on the diarization results. The typical ABIC distance measure can be seen as a special case of the new ABIC distance measure. Our experiment results show that the new distance measurement consistently improves the speaker diarization performance on three datasets.