Robustness of forensic speaker verification systems based on Alize/Lia_Ral toolkit

Author

Bellomo, Francesco ; Beritelli, Francesco ; Sciacca, Eva

Author_Institution

Dipt. di Ing. Elettr., Elettron. ed Inf., Univ. of Catania, Catania, Italy

fYear

2014

fDate

17-17 Oct. 2014

Firstpage

92

Lastpage

97

Abstract

This paper presents the performance analysis of Alize/Lia_Ral algorithms in forensic speaker verification applications. In particular, in this work we evaluate the performance impact of speech signal degradation considering the background noise level, speech rate variation, audio signal length used for testing, GSM radio channel, etc. The Alize/Lia_Ral platform has demonstrated a strong dependence on the ambient noise and a slight dependence on Lombard effect, bandwidth reduction, length of the audio signal, and changes in speech rate.

Keywords

audio signal processing; cellular radio; speaker recognition; Alize/Lia_Ral toolkit; GSM radio channel; Lombard effect; ambient noise; audio signal length; background noise level; bandwidth reduction; forensic speaker verification systems robustness; performance analysis; speech rate variation; speech signal degradation; Databases; Degradation; GSM; Robustness; Signal to noise ratio; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometric Measurements and Systems for Security and Medical Applications (BIOMS) Proceedings, 2014 IEEE Workshop on

Conference_Location

Rome

Print_ISBN

978-1-4799-5175-8

Type

conf

DOI

10.1109/BIOMS.2014.6951542

Filename

6951542