Combating Reverberation in Speaker Verification

Author

Gammal, Joseph S. ; Goubran, Rafik A.

Author_Institution

Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, Ont.

Volume

1

fYear

2005

fDate

16-19 May 2005

Firstpage

687

Lastpage

690

Abstract

This paper investigates reverberation in speaker verification. Reverberant test speech degrades the performance of speaker verification algorithms. The effect of training with speech originating from reverberant environments that are different from that of the test speech is investigated. It was found that with the room impulse responses used, that training with speech that is less reverberant than the test speech always improved performance. A method was proposed to determine given a set of reverberant training speech segments corrupted with different transfer functions, which transfer function corrupted the speech. A classification rate of 96.5% was achieved

Keywords

reverberation; speech processing; speech recognition; reverberation; speaker recognition; speaker verification algorithms; speech processing; transfer functions; Degradation; Forensics; Hidden Markov models; Microphone arrays; Reverberation; Speaker recognition; Speech; Systems engineering and theory; Testing; Transfer functions; Auto-regressive vector model; Pattern classification; Reverberation; Security applications; Speaker Recognition; Speaker Verification; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2005. IMTC 2005. Proceedings of the IEEE

Conference_Location

Ottawa, Ont.

Print_ISBN

0-7803-8879-8

Type

conf

DOI

10.1109/IMTC.2005.1604205

Filename

1604205