On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation

Speaker recognition from speech signal is still an ongoing research in forensics and biometrics area. Speaker recognition is the process to enable machine to recognize speaker's identity from their speech. Recent development on classify speaker data from a group of speaker is still insufficient...

Full description

Bibliographic Details
Main Authors: Ahmad, Abdul Manan, Loh, Mun Yee
Format: Article
Language:English
Published: Penerbit UTM Press 2008
Subjects:
Online Access:http://eprints.utm.my/11021/
http://eprints.utm.my/11021/1/AbdulMananAhmad2008_OnTheImpactOfUsingOptimizationSearch.pdf
_version_ 1848892237741555712
author Ahmad, Abdul Manan
Loh, Mun Yee
author_facet Ahmad, Abdul Manan
Loh, Mun Yee
author_sort Ahmad, Abdul Manan
building UTeM Institutional Repository
collection Online Access
description Speaker recognition from speech signal is still an ongoing research in forensics and biometrics area. Speaker recognition is the process to enable machine to recognize speaker's identity from their speech. Recent development on classify speaker data from a group of speaker is still insufficient to provide a satisfied result in achieving high performance pattern classification engine. There are two main difficulties in this field: how to maintain accuracy rate under incremental amounts of training data and how to reduce the time processing in the case embedded systems need to consider about efficient and simplicity of calculation. Recently we have proposed three difference hybrid pattern classification approach for text independent speaker identification system; in these approaches, we combined a hybrid GMMNQ and decision Tree model. The aim of this paper is to show the progress of the development of a high impact hybrid modeling. Besides, via this paper, an evaluation is done to verify the impact of using optimization search method on large speaker database.
first_indexed 2025-11-15T21:10:40Z
format Article
id utm-11021
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T21:10:40Z
publishDate 2008
publisher Penerbit UTM Press
recordtype eprints
repository_type Digital Repository
spelling utm-110212017-11-01T04:17:21Z http://eprints.utm.my/11021/ On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation Ahmad, Abdul Manan Loh, Mun Yee QA75 Electronic computers. Computer science Speaker recognition from speech signal is still an ongoing research in forensics and biometrics area. Speaker recognition is the process to enable machine to recognize speaker's identity from their speech. Recent development on classify speaker data from a group of speaker is still insufficient to provide a satisfied result in achieving high performance pattern classification engine. There are two main difficulties in this field: how to maintain accuracy rate under incremental amounts of training data and how to reduce the time processing in the case embedded systems need to consider about efficient and simplicity of calculation. Recently we have proposed three difference hybrid pattern classification approach for text independent speaker identification system; in these approaches, we combined a hybrid GMMNQ and decision Tree model. The aim of this paper is to show the progress of the development of a high impact hybrid modeling. Besides, via this paper, an evaluation is done to verify the impact of using optimization search method on large speaker database. Penerbit UTM Press 2008-12 Article PeerReviewed application/pdf en http://eprints.utm.my/11021/1/AbdulMananAhmad2008_OnTheImpactOfUsingOptimizationSearch.pdf Ahmad, Abdul Manan and Loh, Mun Yee (2008) On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation. Jurnal Teknologi Maklumat, 20 (3). pp. 158-172. ISSN 0128-3790
spellingShingle QA75 Electronic computers. Computer science
Ahmad, Abdul Manan
Loh, Mun Yee
On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title_full On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title_fullStr On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title_full_unstemmed On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title_short On the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
title_sort on the impact of using optimization search method in large speaker database based on hybrid modeling over experimental investigation
topic QA75 Electronic computers. Computer science
url http://eprints.utm.my/11021/
http://eprints.utm.my/11021/1/AbdulMananAhmad2008_OnTheImpactOfUsingOptimizationSearch.pdf