Robust Parameters for Automatic Segmentation of Speech

SaiJayram, AKV and Ramasubramanian, V and Sreenivas, TV (2002) Robust Parameters for Automatic Segmentation of Speech. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002.(ICASSP '02), 13-17 May, Orlando,Florida,USA, Vol.1, 513-516.

Preview

PDF robust.pdf Download (669kB)

Abstract

Automatic segmentation of speech ir on important problem that is useful in speed recognition, synthesis and coding. We explore in this paper: the robust parameter set, weightingfunction and distance measure for reliable segmentation of noisy speech. It is found that the MFCC parometers, successful in speech recognition. holds the best promise far robust segmentation also. We also explored a variery of symmetric and asymmetric weighting lifter, from which it is found that a symmetric lifter of the form $1+{Asin^{1/2}}{(\pi n/L)}$, ${0}\leq{n}\leq{L-1}$, for MFCC dimension L, is most effective. With regard to distance measure. the direct $L_2$ norm is found adequate.

Item Type:	Conference Paper
Publisher:	IEEE
Additional Information:	Copyright 1990 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	18 Jan 2006
Last Modified:	19 Sep 2010 04:22
URI:	http://eprints.iisc.ac.in/id/eprint/5026

Actions (login required)

View Item