Skip to content

Detail of publication

Citation

Vaněk, J. and Padrta, A. : Optimization of features for robust speaker recognition . Speech processing, p. 140-147, Academy of Sciences of the Czech Republic, Prague, 2004.

Download PDF

PDF

Abstract

This study is aimed to examine possibilities of improving of the features. Main emphasis is placed on the robustness, i.e. noisy test data and/or channel disturbances (e.g. microphone mismatch). The new proposed features allow us to decrease the recognition error rate by 35-50%.

Detail of publication

Title: Optimization of features for robust speaker recognition
Author: Vaněk, J. ; Padrta, A.
Language: English
Date of publication: 13 Sep 2004
Year: 2004
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Speech processing
Page: 140 - 147
ISBN: 80-86269-11-6
Publisher: Academy of Sciences of the Czech Republic
Address: Prague
Date: 13 Sep 2004 - 15 Sep 2004
/ 2012-02-17 10:56:49 /

Keywords

signal, speech processing, speaker recognition, verification, identification, robustness, features, noise, channel, distortion, MFCC, PLP, CMS, filter, smoothing, GMM, UBM

BibTeX

@INPROCEEDINGS{VanekJ_2004_Optimizationof,
 author = {Van\v{e}k, J. and Padrta, A.},
 title = {Optimization of features for robust speaker recognition},
 year = {2004},
 publisher = {Academy of Sciences of the Czech Republic},
 journal = {Speech processing},
 address = {Prague},
 pages = {140-147},
 ISBN = {80-86269-11-6},
 url = {http://www.kky.zcu.cz/en/publications/VanekJ_2004_Optimizationof},
}