A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach

A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach

This paper reports an approach that depends on Continuous Hidden Markov Models (CHMMs) to identify Arabic speakers automatically from their voices. The Mel-Frequency Cepstral Coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM is developed...

Full description

Bibliographic Details
Main Author: Hesham Tolba
Format: Article
Language:English
Published: Elsevier 2011-03-01
Series:Alexandria Engineering Journal
Subjects:
Speaker identification
CHMMs
Statistical recognition
Arabic speaker recognition
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016811000159
id doaj-5a5103a9798c44628718b1b2474887ae
record_format Article
spelling doaj-5a5103a9798c44628718b1b2474887ae2021-06-02T18:29:19ZengElsevierAlexandria Engineering Journal1110-01682011-03-01501434710.1016/j.aej.2011.01.007A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approachHesham TolbaThis paper reports an approach that depends on Continuous Hidden Markov Models (CHMMs) to identify Arabic speakers automatically from their voices. The Mel-Frequency Cepstral Coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM is developed for the CHMM system. Ten Arabic speakers were used to evaluate our proposed CHMM-based engine. The identification rate was found to be 100% during text dependent experiments. However, for the text-independent experiments, the identification rate was found to be 80%.http://www.sciencedirect.com/science/article/pii/S1110016811000159Speaker identificationCHMMsStatistical recognitionArabic speaker recognition
collection DOAJ
language English
format Article
sources DOAJ
author Hesham Tolba
spellingShingle Hesham Tolba
A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
Alexandria Engineering Journal
Speaker identification
CHMMs
Statistical recognition
Arabic speaker recognition
author_facet Hesham Tolba
author_sort Hesham Tolba
title A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
title_short A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
title_full A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
title_fullStr A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
title_full_unstemmed A high-performance text-independent speaker identification of Arabic speakers using a CHMM-based approach
title_sort high-performance text-independent speaker identification of arabic speakers using a chmm-based approach
publisher Elsevier
series Alexandria Engineering Journal
issn 1110-0168
publishDate 2011-03-01
description This paper reports an approach that depends on Continuous Hidden Markov Models (CHMMs) to identify Arabic speakers automatically from their voices. The Mel-Frequency Cepstral Coefficients (MFCCs) were selected to describe the speech signal. The general Gaussian density distribution HMM is developed for the CHMM system. Ten Arabic speakers were used to evaluate our proposed CHMM-based engine. The identification rate was found to be 100% during text dependent experiments. However, for the text-independent experiments, the identification rate was found to be 80%.
topic Speaker identification
CHMMs
Statistical recognition
Arabic speaker recognition
url http://www.sciencedirect.com/science/article/pii/S1110016811000159
work_keys_str_mv AT heshamtolba ahighperformancetextindependentspeakeridentificationofarabicspeakersusingachmmbasedapproach
AT heshamtolba highperformancetextindependentspeakeridentificationofarabicspeakersusingachmmbasedapproach
_version_ 1721402172701147136

Similar Items