logo Idiap Research Institute        
 [BibTeX] [Marc21]
Unknown-Multiple Speaker clustering using HMM
Type of publication: Conference paper
Citation: ajmera2002icslp
Booktitle: ICSLP
Year: 2002
Address: Denver, Colorado
Note: IDIAP-RR 02-07
Crossref: ajmera-rr-02-07:
Abstract: An HMM-based speaker clustering framework is presented, where the number of speakers and segmentation boundaries are unknown \emph{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.
Userfields: ipdmembership={speech},
Projects Idiap
Authors Ajmera, Jitendra
Bourlard, Hervé
Lapidot, I.
McCowan, Iain A.
Added by: [UNK]
Total mark: 0
  • ajmera2002icslp.pdf
  • ajmera2002icslp.ps