Speaker Diarization System Based on GMM and BIC

This paper presents an approach for speaker diarization based on a novel combination of Gaussian mixture model (GMM) and standard Bayesian information criterion (BIC). Gaussian mixture model provides a good description of feature vector distribution and BIC enables a proper merging and stopping criterion. Our system combines the advantage of these two method and yields favorable performance. Experiments carried out on mandarin broadcast news data demonstrate the advantage of the proposed approach, which shows better performance than the approach only based on GMM clustering.