Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools

This paper reports the design, implementation, and evaluation of a research work for developing a high performance natural speaker-independent Arabic continuous speech recognition system. It aims to explore the usefulness and success of a newly developed speech corpus, which is phonetically rich and...

Full description

Bibliographic Details
Main Authors:	Abushariah, Mohammad A. M., Ainon, Raja N., Zainuddin, Roziati, Elshafei, Moustafa, Khalifa, Othman Omran
Format:	Conference or Workshop Item
Language:	English
Published:	2010
Subjects:	T Technology (General)
Online Access:	http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/1/05556829.pdf

id	iium-5809
recordtype	eprints
spelling	iium-58092011-11-21T22:58:46Z http://irep.iium.edu.my/5809/ Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools Abushariah, Mohammad A. M. Ainon, Raja N. Zainuddin, Roziati Elshafei, Moustafa Khalifa, Othman Omran T Technology (General) This paper reports the design, implementation, and evaluation of a research work for developing a high performance natural speaker-independent Arabic continuous speech recognition system. It aims to explore the usefulness and success of a newly developed speech corpus, which is phonetically rich and balanced, presenting a competitive approach towards the development of an Arabic ASR system as compared to the state-of-the-art Arabic ASR researches. The developed Arabic AS R mainly used the Carnegie Mellon University (CMU) Sphinx tools together with the Cambridge HTK tools. To extract features from speech signals, Mel-Frequency Cepstral Coefficients (MFCC) technique was applied producing a set of feature vectors. Subsequently, the system uses five-state Hidden Markov Models (HMM) with three emitting states for tri-phone acoustic modeling. The emission probability distribution of the states was best using continuous density 16 Gaussian mixture distributions. The state distributions were tied to 500 senons. The language model contains uni-grams, bi-grams, and tri-grams. The system was trained on 7.0 hours of phonetically rich and balanced Arabic speech corpus and tested on another one hour. For similar speakers but different sentences, the system obtained a word recognition accuracy of 92.67% and 93.88% and a Word Error Rate (WER) of 11.27% and 10.07% with and without diacritical marks respectively. For different speakers but similar sentences, the system obtained a word recognition accuracy of 95.92% and 96.29% and a Word Error Rate (WER) of 5.78% and 5.45% with and without diacritical marks respectively. Whereas different speakers and different sentences, the system obtained a word recognition accuracy of 89.08% and 90.23% and a Word Error Rate (WER) of 15.59% and 14.44% with and without diacritical marks respectively. 2010 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/5809/1/05556829.pdf Abushariah, Mohammad A. M. and Ainon, Raja N. and Zainuddin, Roziati and Elshafei, Moustafa and Khalifa, Othman Omran (2010) Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools. In: International Conference on Computer and Communication Engineering (ICCCE 2010), 11-13 May 2010, Kuala Lumpur. http://dx.doi.org/10.1109/ICCCE.2010.5556829 doi:10.1109/ICCCE.2010.5556829
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	T Technology (General)
spellingShingle	T Technology (General) Abushariah, Mohammad A. M. Ainon, Raja N. Zainuddin, Roziati Elshafei, Moustafa Khalifa, Othman Omran Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
description	This paper reports the design, implementation, and evaluation of a research work for developing a high performance natural speaker-independent Arabic continuous speech recognition system. It aims to explore the usefulness and success of a newly developed speech corpus, which is phonetically rich and balanced, presenting a competitive approach towards the development of an Arabic ASR system as compared to the state-of-the-art Arabic ASR researches. The developed Arabic AS R mainly used the Carnegie Mellon University (CMU) Sphinx tools together with the Cambridge HTK tools. To extract features from speech signals, Mel-Frequency Cepstral Coefficients (MFCC) technique was applied producing a set of feature vectors. Subsequently, the system uses five-state Hidden Markov Models (HMM) with three emitting states for tri-phone acoustic modeling. The emission probability distribution of the states was best using continuous density 16 Gaussian mixture distributions. The state distributions were tied to 500 senons. The language model contains uni-grams, bi-grams, and tri-grams. The system was trained on 7.0 hours of phonetically rich and balanced Arabic speech corpus and tested on another one hour. For similar speakers but different sentences, the system obtained a word recognition accuracy of 92.67% and 93.88% and a Word Error Rate (WER) of 11.27% and 10.07% with and without diacritical marks respectively. For different speakers but similar sentences, the system obtained a word recognition accuracy of 95.92% and 96.29% and a Word Error Rate (WER) of 5.78% and 5.45% with and without diacritical marks respectively. Whereas different speakers and different sentences, the system obtained a word recognition accuracy of 89.08% and 90.23% and a Word Error Rate (WER) of 15.59% and 14.44% with and without diacritical marks respectively.
format	Conference or Workshop Item
author	Abushariah, Mohammad A. M. Ainon, Raja N. Zainuddin, Roziati Elshafei, Moustafa Khalifa, Othman Omran
author_facet	Abushariah, Mohammad A. M. Ainon, Raja N. Zainuddin, Roziati Elshafei, Moustafa Khalifa, Othman Omran
author_sort	Abushariah, Mohammad A. M.
title	Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
title_short	Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
title_full	Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
title_fullStr	Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
title_full_unstemmed	Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools
title_sort	natural speaker-independent arabic speech recognition system based on hidden markov models using sphinx tools
publishDate	2010
url	http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/ http://irep.iium.edu.my/5809/1/05556829.pdf
first_indexed	2023-09-18T20:14:35Z
last_indexed	2023-09-18T20:14:35Z
_version_	1777407702841950208

Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools

Similar Items