A composite signal subspace speech classifier

Recently, a speech model inspired by signal subspace methods was proposed for a speech classifier. In using subspace information to characterize the speech signal, subspace trajectories in the form of the right singular vectors of the measurement matrices are obtained. Signal classification is there...

Full description

Bibliographic Details
Main Authors: TAN, A, RAO, M, DAYASAGAR, B
Format: Article
Language:English
Published: ELSEVIER SCIENCE BV 2007
Subjects:
Online Access:http://shdl.mmu.edu.my/2983/
http://shdl.mmu.edu.my/2983/1/1013.pdf
_version_ 1848790201943457792
author TAN, A
RAO, M
DAYASAGAR, B
author_facet TAN, A
RAO, M
DAYASAGAR, B
author_sort TAN, A
building MMU Institutional Repository
collection Online Access
description Recently, a speech model inspired by signal subspace methods was proposed for a speech classifier. In using subspace information to characterize the speech signal, subspace trajectories in the form of the right singular vectors of the measurement matrices are obtained. Signal classification is thereafter accomplished by a minimum-distance rule with noteworthy results. This paper extends the foregoing approach by organizing the vector trajectories into matrices. The matrices so obtained are the reduced-rank approximation of the sample correlation matrices. A new dissimilarity measure in the Frobenius norm is correspondingly proposed for the matrix trajectories. Simulation results of the proposed composite signal subspace classifier in an isolated digit speech recognition problem reveal an improved performance over its predecessor. Additionally, the results also show the proposed classifier retaining the white noise robustness of the original design. (c) 2007 Elsevier B.V. All rights reserved.
first_indexed 2025-11-14T18:08:51Z
format Article
id mmu-2983
institution Multimedia University
institution_category Local University
language English
last_indexed 2025-11-14T18:08:51Z
publishDate 2007
publisher ELSEVIER SCIENCE BV
recordtype eprints
repository_type Digital Repository
spelling mmu-29832014-02-13T09:06:44Z http://shdl.mmu.edu.my/2983/ A composite signal subspace speech classifier TAN, A RAO, M DAYASAGAR, B T Technology (General) QA75.5-76.95 Electronic computers. Computer science Recently, a speech model inspired by signal subspace methods was proposed for a speech classifier. In using subspace information to characterize the speech signal, subspace trajectories in the form of the right singular vectors of the measurement matrices are obtained. Signal classification is thereafter accomplished by a minimum-distance rule with noteworthy results. This paper extends the foregoing approach by organizing the vector trajectories into matrices. The matrices so obtained are the reduced-rank approximation of the sample correlation matrices. A new dissimilarity measure in the Frobenius norm is correspondingly proposed for the matrix trajectories. Simulation results of the proposed composite signal subspace classifier in an isolated digit speech recognition problem reveal an improved performance over its predecessor. Additionally, the results also show the proposed classifier retaining the white noise robustness of the original design. (c) 2007 Elsevier B.V. All rights reserved. ELSEVIER SCIENCE BV 2007-11 Article NonPeerReviewed text en http://shdl.mmu.edu.my/2983/1/1013.pdf TAN, A and RAO, M and DAYASAGAR, B (2007) A composite signal subspace speech classifier. Signal Processing, 87 (11). pp. 2600-2606. ISSN 01651684 http://dx.doi.org/10.1016/j.sigpro.2007.04.009 doi:10.1016/j.sigpro.2007.04.009 doi:10.1016/j.sigpro.2007.04.009
spellingShingle T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
TAN, A
RAO, M
DAYASAGAR, B
A composite signal subspace speech classifier
title A composite signal subspace speech classifier
title_full A composite signal subspace speech classifier
title_fullStr A composite signal subspace speech classifier
title_full_unstemmed A composite signal subspace speech classifier
title_short A composite signal subspace speech classifier
title_sort composite signal subspace speech classifier
topic T Technology (General)
QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2983/
http://shdl.mmu.edu.my/2983/
http://shdl.mmu.edu.my/2983/
http://shdl.mmu.edu.my/2983/1/1013.pdf