Share Email Print
cover

Proceedings Paper

Estimating speaker scale factors from vowels
Author(s): Douglas J. Nelson; David C. Smith; Srinivasan Umesh; Leon Cohen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In previous works, Umesh et al, demonstrated that phonetically similar vowels spoken by different individuals are related by a simple translation in a universal warped spectral representation. They experimentally derived this function and called it the “speech-scale”. We present further experimental evidence, based on a large data set, validating the speech-scale. We also estimate speaker-specific scale factors based on the speech-scale, and we present a vowel classification experiment, which demonstrates a significant performance improvement through a normalization based on the speech-scale. The results we present are based on formant estimates of vowels in a Western Michigan vowel database.

Paper Details

Date Published: 13 November 2003
PDF: 7 pages
Proc. SPIE 5207, Wavelets: Applications in Signal and Image Processing X, (13 November 2003); doi: 10.1117/12.507416
Show Author Affiliations
Douglas J. Nelson, U.S. Dept. of Defense (United States)
David C. Smith, U.S. Dept. of Defense (United States)
Srinivasan Umesh, Indian Institute of Technology Kanpur (India)
Leon Cohen, CUNY/Hunter College (United States)


Published in SPIE Proceedings Vol. 5207:
Wavelets: Applications in Signal and Image Processing X
Michael A. Unser; Akram Aldroubi; Andrew F. Laine, Editor(s)

© SPIE. Terms of Use
Back to Top