Infinite Models for Speaker Clustering

In this paper we propose the use of infinite models for the clustering of speakers. Speaker segmentation is obtained trough a Dirichlet Process Mixture (DPM) model which can be interpreted as a flexible model with an infinite a priori number of components. Learning is based on a Variational Bayesian approximation of the infinite sequence. DPM model is compared with fixed prior systems learned by ML/BIC, MAP/BIC and a Variational Bayesian method. Experiments are run on a speaker clustering task on the NIST-96 Broadcast News database.


Presented at:
International Conference on Spoken Language Processing
Year:
2006
Note:
IDIAP-RR 06-19
Laboratories:




 Record created 2010-02-11, last modified 2018-03-17

n/a:
Download fulltextPDF
External links:
Download fulltextURL
Download fulltextRelated documents
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)