DMCA
Speaker Diarization using bottom-up clustering based on a Parameter-derived Distance between adapted GMMs (2004)
| Venue: | in "Intl. Conf. on Speech and Language Processing |
| Citations: | 25 - 2 self |
BibTeX
@INPROCEEDINGS{Ben04speakerdiarization,
author = {Mathieu Ben and Michaël Betser and Frédéric Bimbot and Guillaume Gravier},
title = {Speaker Diarization using bottom-up clustering based on a Parameter-derived Distance between adapted GMMs},
booktitle = {in "Intl. Conf. on Speech and Language Processing},
year = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, we present an approach for speaker diarization based on segmentation followed by bottom-up clustering, where clusters are modeled using adapted Gaussian mixture models. We propose a novel inter-cluster distance in the model parameter space which is easily computable and which can both be used as the dissimilarity measure in the clustering scheme and as a stop criterion. Using adapted Gaussian mixture models enables a good description of the feature vector distribution within a cluster while adaptation prevents over-training for clusters with few data. Experiments carried out on broadcast news data in French demonstrate the potential of the proposed approach which exhibits performance similar to BIC clustering. However, our clustering method appeared to be more sensitive to segmentation errors than the BIC approach. 1.
Keyphrases
speaker diarization bottom-up clustering parameter-derived distance adapted gaussian mixture model model parameter space feature vector distribution novel inter-cluster distance broadcast news data stop criterion good description clustering scheme bic clustering segmentation error dissimilarity measure bic approach adaptation prevents
