Speaker verification by removing common information

Yiying Zhang, Xiaoyan Zhu, Dapeng Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

A new speaker verification method is presented which is based on likelihood score normalisation and employs the global speaker model. As a result of the normalisation, common speech and environmental factors are removed from input utterances so that differences between speakers are emphasised. Experimental results of text-independent verification tests show the effectiveness of this method.
Original languageEnglish
Pages (from-to)2009-2011
Number of pages3
JournalElectronics Letters
Volume35
Issue number23
DOIs
Publication statusPublished - 11 Nov 1999

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Speaker verification by removing common information'. Together they form a unique fingerprint.

Cite this