Institut for Forretningsudvikling og Teknologi

Ramjee Prasad

Multi-Frame Rate Based Multiple-Model Training for Robust Speaker Identification of Disguised Voice

Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

Speaker identification systems are prone to attack when voice disguise is adopted by the user. To address this issue,our paper studies the effect of using different frame rates on the accuracy of the speaker identification system for disguised voice.In addition, a multi-frame rate based multiple-model training method is proposed. The experimental results show the superior performance of the proposed method compared to the commonly used single frame rate method for three types of disguised voice taken from the CHAINS corpus.
OriginalsprogEngelsk
Titel16th Wireless Personal Multimedia Communications Symposium (WPMC'13), Atlantic City, New Jersey, USA
Antal sider4
ForlagIEEE Press
Udgivelsesår2013
Sider1 - 4
StatusUdgivet - 2013
Eksternt udgivetJa
BegivenhedWireless Personal Multimedia Communications Symposium (WPMC'13) - Atlantic, New Jersey, USA
Varighed: 24 jun. 201327 jun. 2013

Konference

KonferenceWireless Personal Multimedia Communications Symposium (WPMC'13)
LokationAtlantic
LandUSA
ByNew Jersey
Periode24/06/201327/06/2013
SerietitelProceedings of the Wireless Personal Multimedia Communications Symposia
ISSN1347-6890

Se relationer på Aarhus Universitet Citationsformater

ID: 171386166