University of Hertfordshire

From the same journal

By the same authors

Verification Effectiveness in Open-Set Speaker Identification

Research output: Contribution to journalArticle

Links

View graph of relations
Original languageEnglish
Pages (from-to)618-624
JournalIEE Proceedings - Vision, Image and Signal Processing
Journal publication date1 Oct 2006
Volume153
Issue5
DOIs
Publication statusPublished - 1 Oct 2006

Abstract

Verification effectiveness in open-set, text-independent speaker identification. The study includes an analysis of the characteristics of this mode of speaker recognition and the potential causes of errors. The use of well-known score normalisation techniques for the purpose enhancing the reliability of the process is described and their relative effectiveness is experimentally investigated. The experiments are based on the dataset proposed for the 1-speaker detection task of the NIST Speaker Recognition Evaluation 2003. Based on the experimental results, it is demonstrated that significant benefits is achieved by using score normalisation in open-set identification, and that the level of this depends highly on the type of the approach adopted. The results also show that better performance can be achieved by using the cohort normalisation methods. In particular, the unconstrained cohort method with a relatively small cohort size appears to outperform all other approaches.

Notes

This paper is a postprint of a paper submitted to and accepted for publication in IEE Proceedings Vision, Image and Signal Processing and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.

ID: 16011626