ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

KL realignment for speaker diarization with multiple feature streams

Deepu Vijayasenan, Fabio Valente, Hervé Bourlard

This paper aims at investigating the use of Kullback-Leibler (KL) divergence based realignment with application to speaker diarization. The use of KL divergence based realignment operates directly on the speaker posterior distribution estimates and is compared with traditional realignment performed using HMM/GMM system. We hypothesize that using posterior estimates to re-align speaker boundaries is more robust than gaussian mixture models in case of multiple feature streams with different statistical properties. Experiments are run on the NIST RT06 data. These experiments reveal that in case of conventional MFCC features the two approaches yields the same performance while the KL based system outperforms the HMM/GMM re-alignment in case of combination of multiple feature streams (MFCC and TDOA).

doi: 10.21437/Interspeech.2009-325

Cite as: Vijayasenan, D., Valente, F., Bourlard, H. (2009) KL realignment for speaker diarization with multiple feature streams. Proc. Interspeech 2009, 1059-1062, doi: 10.21437/Interspeech.2009-325

  author={Deepu Vijayasenan and Fabio Valente and Hervé Bourlard},
  title={{KL realignment for speaker diarization with multiple feature streams}},
  booktitle={Proc. Interspeech 2009},