Share Email Print

Proceedings Paper

Alternative linear predictive analysis techniques with applications to speaker identification
Author(s): Ravi P. Ramachandran; M. S. Zilovic; Richard J. Mammone
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, various linear predictive (LP) analysis methods are studied and compared from the points of view of robustness to noise and of application to speaker identification. The key of the success of LP techniques is in separating the vocal tract information from the pitch information present in a speech signal even under noisy conditions. In addition to considering the conventional, one-shot weighted least-squares methods, we propose three other approaches with the above point as a motivation. The first is an iterative approach that leads to the weighted least absolute value solution. The second is an extension of the one-shot least-squares approach and achieves an iterative update of the weights. The update is a function of the residual and is based on minimizing a Mahalanobis distance. Thirdly, the weighted total least- squares formulation is considered. A study of the deviations in the LP parameters was done when noise (white Gaussian and impulsive) is added to the speech. It was revealed that the most robust method depends on the type of noise. A closed set speaker identification experiment with 20 speakers was conducted using a vector quantizer classifier trained on clean speech. For a modest codebook size of 32, all of the approaches are comparable when the testing condition corresponds to clean speech or speech degraded by white Gaussian noise. When the test involves speech degraded by impulse noise, the proposed approach based on minimizing a Mahalanobis distance which was found to be the most robust, is also the best for speaker identification.

Paper Details

Date Published: 25 October 1994
PDF: 12 pages
Proc. SPIE 2277, Automatic Systems for the Identification and Inspection of Humans, (25 October 1994); doi: 10.1117/12.191870
Show Author Affiliations
Ravi P. Ramachandran, Rutgers Univ. (United States)
M. S. Zilovic, Rutgers Univ. (United States)
Richard J. Mammone, Rutgers Univ. (United States)

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

© SPIE. Terms of Use
Back to Top