Share Email Print

Proceedings Paper

Robust matching for voice recognition
Author(s): Alan Higgins; L. Bahler; J. Porter; P. Blais
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes an automated method of comparing a voice sample of an unknown individual with samples from known speakers in order to establish or verify the individual's identity. The method is based on a statistical pattern matching approach that employs a simple training procedure, requires no human intervention (transcription, work or phonetic marketing, etc.), and makes no assumptions regarding the expected form of the statistical distributions of the observations. The content of the speech material (vocabulary, grammar, etc.) is not assumed to be constrained in any way. An algorithm is described which incorporates frame pruning and channel equalization processes designed to achieve robust performance with reasonable computational resources. An experimental implementation demonstrating the feasibility of the concept is described.

Paper Details

Date Published: 25 October 1994
PDF: 4 pages
Proc. SPIE 2277, Automatic Systems for the Identification and Inspection of Humans, (25 October 1994); doi: 10.1117/12.191871
Show Author Affiliations
Alan Higgins, ITT Aerospace (United States)
L. Bahler, ITT Aerospace (United States)
J. Porter, ITT Aerospace (United States)
P. Blais, ITT Aerospace (United States)

Published in SPIE Proceedings Vol. 2277:
Automatic Systems for the Identification and Inspection of Humans
Richard J. Mammone; J. David Murley Jr., Editor(s)

© SPIE. Terms of Use
Back to Top