A new penalty term for the BIC with respect to speaker diarization

Stafylakis, T. and Tzimiropoulos, G. and Katsouros, V. and Carayannis, G. (2010) A new penalty term for the BIC with respect to speaker diarization. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP, 14 -19 March 2010, Dallas, Texas.

Full content URL: http://dx.doi.org/10.1109/ICASSP.2010.5495076

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

In this paper we examine a new penalty term for the Bayesian Information Criterion (BIC) that is suited to the problem of speaker diarization. Based on our previous approach of penalizing each cluster only with its effective sample size - an approach we called segmental - we propose a stricter penalty term. The criterion we derive retains the main property of the Segmental-BIC, i.e. it approximates the evidence of overall partitions of the data and simultaneously leads to a pairwise dissimilarity measure that is completely defined by the pair of clusters in question. The experimental results show significant improvement in diarization accuracy on the ESTER benchmark. ©2010 IEEE.

Additional Information:Conference Code: 81981
Keywords:Bayesian information criterion, Dissimilarity measures, Penalty term, Sample sizes, Speaker diarization, Cluster analysis, Esters, Signal processing, Bayesian networks
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:8734
Deposited On:01 Aug 2013 11:39

Repository Staff Only: item control page