Variational Bayesian speaker clustering

In this paper we explore the use of Variational Bayesian (VB) learning in unsupervised speaker clustering. VB learning is a relatively new learning technique that has the capacity of doing at the same time parameter learning and model selection. We tested this approach on the NIST 1996 HUB-4 evaluation test for speaker clustering when the speaker number is a priori known and when it has to be estimated. VB shows a higher accuracy in terms of average cluster purity and average speaker purity compared to the Maximum Likelihood solution.