Unsupervised speaker clustering using SVM training missclassification rate for meeting short-duration speech signals

Po Chuan Lin, Yeh Yi Jui, Tsai Sung Ying, Yeong Chin Chen, Menq Jion Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an unsupervised speaker clustering system for duration of speech signals below 4 seconds. For determining whether two collected speech sections uttered from the same speaker or not, our previous SVM training miss-classification rate (STMR) is adopted to evaluate the data separability between two different speakers. This paper also proposes a hierarchical extract and merge (HEM) clustering method to reduce agglomeration time and enhance the clustering purity. Experiment results show the average speaker purity (ASP) and average cluster purity (ACP) are both better than the CE manner with the GMM training miss-classification rates (GTMR) for 2 to 4 seconds short speech sections.

Original languageEnglish
Title of host publicationProceedings - 4th International Conference on Genetic and Evolutionary Computing, ICGEC 2010
Pages606-609
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Event4th International Conference on Genetic and Evolutionary Computing, ICGEC 2010 - Shenzhen, China
Duration: 2010 Dec 132010 Dec 15

Publication series

NameProceedings - 4th International Conference on Genetic and Evolutionary Computing, ICGEC 2010

Other

Other4th International Conference on Genetic and Evolutionary Computing, ICGEC 2010
CountryChina
CityShenzhen
Period10-12-1310-12-15

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Unsupervised speaker clustering using SVM training missclassification rate for meeting short-duration speech signals'. Together they form a unique fingerprint.

Cite this