7th International Conference on Spoken Language Processing
September 16-20, 2002
An HMM-based speaker clustering framework is presented, where the number of speakers and segmentation boundaries are unknown a priori. Ideally, the system aims to create one pure cluster for each speaker. The HMM is ergodic in nature with a minimum duration topology. The final number of clusters is determined automatically by merging closest clusters and retraining this new cluster, until a decrease in likelihood is observed. In the same framework, we also examine the effect of using only the features from highly voiced frames as a means of improving the robustness and computational complexity of the algorithm. The proposed system is assessed on the 1996 HUB-4 evaluation test set in terms of both cluster and speaker purity. It is shown that the number of clusters found often correspond to the actual number of speakers.
Bibliographic reference. Ajmera, J. / Bourlard, Hervé / Lapidot, I. / McCowan, Iain A. (2002): "Unknown-multiple speaker clustering using HMM", In ICSLP-2002, 573-576.