Title: Speaker identification based on vector quantization
Other Titles: Identifikace řečníka na základě vektorové kvantizace
Authors: Radová, Vlasta
Švenda, Zdeněk
Citation: RADOVÁ, Vlasta; ŠVENDA, Zdeněk. Speaker identification based on vector quantization. In: Text, speech and dialogue. Berlin: Springer, 1999, p. 341-344. (Lecture notes in computer science; 1692). ISBN 3-540-66494-7.
Issue Date: 1999
Publisher: Springer
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/RadovaV_1999_SpeakerIdenti
ISBN: 3-540-66494-7
Keywords: identifikace řečníka;vektorová kvantizace
Keywords in different language: speaker identification;vector quantization
Abstract in different language: In this paper a method of text-independent speaker recognition using discrete vector quantization is presented. The identification experiments were performed in a closed set of 599 speakers and two various types of features were tested: cepstral mean subtraction coeficients and mel-frequency cepstral coeficients. The effect of the various codebook size on the speaker identification performance was investigated.
Rights: © Vlasta Radová - Zdeněk Švenda
Appears in Collections:Články / Articles (KKY)

Files in This Item:
File Description SizeFormat 
RadovaV_1999_SpeakerIdenti.pdfPlný text89,87 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/16996

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.