Eigen-prpsody analysis for robust speaker recognition under mismatch handset environment

Z. H. Chen, Y. F. Liao, Y. T. Juang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

A novel eigen-prosody analysis approach is proposed for robust speaker recognition under a mismatch handset environment. The idea is to convert the prosodie contours of a speaker's speech into sequences of prosody symbols, and transform the speaker recognition problem into a full-text document retrieval-similar task. Experimental results on the HTIMIT corpus have shown that, even though only few training/test data are available, about 32.2% relative error rate reduction could be achieved compared with the conventional Gaussian mixture model/cepstral mean subtraction approach.

Original languageEnglish
Pages (from-to)1233-1235
Number of pages3
JournalElectronics Letters
Volume40
Issue number19
DOIs
StatePublished - 16 Sep 2004

Cite this