Segmental K-means initialization for SOM-based speaker clustering

Oshry Ben-Harush, Itshak Lapidot, Hugo Guterman

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations

Abstract

A new approach for initial assignment of data in a speaker clustering application is presented. This approach employs Segmental K-Means clustering algorithm prior to competitive based learning. The clustering system relies on Self-Organizing Maps (SOM) for speaker modeling and as a likelihood estimator. Performance is evaluated on 108 two speaker conversations taken from LDC CALLHOME American English Speech corpus using NIST criterion and shows an improvement of 20%-30% in Cluster Error Rate (CER) relative to the randomly initialized clustering system. The number of iterations was reduced significantly, which contributes to both speed and efficiency of the clustering system.

Original languageEnglish
Article number4747495
Pages (from-to)305-308
Number of pages4
JournalProceedings Elmar - International Symposium Electronics in Marine
Volume1
StatePublished - 1 Dec 2008
EventELMAR-2008 - 50th International Symposium ELMAR 2008 - Zadar, Croatia
Duration: 10 Sep 200812 Sep 2008

Keywords

  • Clustering
  • Initial Conditions
  • K-means
  • SOM
  • Speech

Fingerprint

Dive into the research topics of 'Segmental K-means initialization for SOM-based speaker clustering'. Together they form a unique fingerprint.

Cite this