Speaker normalization with the band-pass transform

Author

Dognin, Pierre L. ; El-Jaroudi, Amro

Author_Institution

Dept. of Electr. Eng., Pittsburgh Univ., PA, USA

Volume

2

fYear

2003

fDate

9-12 Nov. 2003

Firstpage

1894

Abstract

This paper presents a new spectral transformation for speaker normalization called the "band-pass transform" (BPT). From the framework of the bilinear transformation (BT), the BPT is a new frequency warping resulting from a mapping of a prototype band-pass (BP) filter into a general BP filter. The BPT offers two degrees of freedom enabling complex warpings of the frequency axis. Estimation of the BPT parameters is performed using the Nelder-Mead algorithm. Our experimental results include a study of the BPT performance. BPT performs better than other VTLN methods and offers a gain of 1.13% absolute on Hub-5 English Eva101 set.

Keywords

band-pass filters; speaker recognition; spectral analysis; transforms; Hub-5 English Eva101 set; Nelder-Mead algorithm; band-pass filter; band-pass transform; bilinear transformation; degrees of freedom; frequency warping; speaker normalization; spectral transformation; Automatic speech recognition; Band pass filters; Degradation; Displays; Frequency; Nonlinear distortion; Performance gain; Prototypes; Shape; Speech analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2004. Conference Record of the Thirty-Seventh Asilomar Conference on

Print_ISBN

0-7803-8104-1

Type

conf

DOI

10.1109/ACSSC.2003.1292311

Filename

1292311