Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems

Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems

This paper describes an efficient framework for designing and developing Arabic speaker-independent continuous automatic speech recognition systems based on a phonetically rich and balanced speech corpus. The speech corpus contains 415 sentences recorded by 42 (21 male and 21 female) Arabic native s...

Full description

Bibliographic Details
Main Authors: Abushariah, Mohammad Abd-Alrahman Mahmoud, Ainon, Raja Noor, 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/6978/
http://irep.iium.edu.my/6978/
http://irep.iium.edu.my/6978/
http://irep.iium.edu.my/6978/1/PHONETICALLY_RICH_AND_BALANCED_SPEECH_CORPUS_FOR_ARABIC_.pdf
id iium-6978
recordtype eprints
spelling iium-69782011-12-14T00:26:48Z http://irep.iium.edu.my/6978/ Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems Abushariah, Mohammad Abd-Alrahman Mahmoud Ainon, Raja Noor Zainuddin, Roziati Elshafei, Moustafa Khalifa, Othman Omran T Technology (General) This paper describes an efficient framework for designing and developing Arabic speaker-independent continuous automatic speech recognition systems based on a phonetically rich and balanced speech corpus. The speech corpus contains 415 sentences recorded by 42 (21 male and 21 female) Arabic native speakers from 11 Arab countries representing three major regions (Levant, Gulf, and Africa). The developed system is based on the Carnegie Mellon University (CMU) Sphinx tools. The Cambridge HTK tools were also used in some testing stages. The speech engine uses 3-emitting state Hidden Markov Models (HMM) for tri-phone based acoustic models. Based on experimental analysis of 4.07 hours of training speech data, the acoustic model used continuous observation's probability model of 16 Gaussian mixture distributions and the state distributions were tied to 400 senons. The language model contains both bi-grams and tri-grams. The system obtained 91.23% and 92.54% correct word recognition with and without diacritical marks respectively. 2010-10-18 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/6978/1/PHONETICALLY_RICH_AND_BALANCED_SPEECH_CORPUS_FOR_ARABIC_.pdf Abushariah, Mohammad Abd-Alrahman Mahmoud and Ainon, Raja Noor and Zainuddin, Roziati and Elshafei, Moustafa and Khalifa, Othman Omran (2010) Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems. In: 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), 10-13 May 2010, Kuala Lumpur, Malaysia. http://dx.doi.org/10.1109/ISSPA.2010.5605554 doi:10.1109/ISSPA.2010.5605554
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 Abd-Alrahman Mahmoud
Ainon, Raja Noor
Zainuddin, Roziati
Elshafei, Moustafa
Khalifa, Othman Omran
Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
description This paper describes an efficient framework for designing and developing Arabic speaker-independent continuous automatic speech recognition systems based on a phonetically rich and balanced speech corpus. The speech corpus contains 415 sentences recorded by 42 (21 male and 21 female) Arabic native speakers from 11 Arab countries representing three major regions (Levant, Gulf, and Africa). The developed system is based on the Carnegie Mellon University (CMU) Sphinx tools. The Cambridge HTK tools were also used in some testing stages. The speech engine uses 3-emitting state Hidden Markov Models (HMM) for tri-phone based acoustic models. Based on experimental analysis of 4.07 hours of training speech data, the acoustic model used continuous observation's probability model of 16 Gaussian mixture distributions and the state distributions were tied to 400 senons. The language model contains both bi-grams and tri-grams. The system obtained 91.23% and 92.54% correct word recognition with and without diacritical marks respectively.
format Conference or Workshop Item
author Abushariah, Mohammad Abd-Alrahman Mahmoud
Ainon, Raja Noor
Zainuddin, Roziati
Elshafei, Moustafa
Khalifa, Othman Omran
author_facet Abushariah, Mohammad Abd-Alrahman Mahmoud
Ainon, Raja Noor
Zainuddin, Roziati
Elshafei, Moustafa
Khalifa, Othman Omran
author_sort Abushariah, Mohammad Abd-Alrahman Mahmoud
title Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
title_short Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
title_full Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
title_fullStr Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
title_full_unstemmed Phonetically rich and balanced speech corpus for Arabic speaker-independent continuous automatic speech recognition systems
title_sort phonetically rich and balanced speech corpus for arabic speaker-independent continuous automatic speech recognition systems
publishDate 2010
url http://irep.iium.edu.my/6978/
http://irep.iium.edu.my/6978/
http://irep.iium.edu.my/6978/
http://irep.iium.edu.my/6978/1/PHONETICALLY_RICH_AND_BALANCED_SPEECH_CORPUS_FOR_ARABIC_.pdf
first_indexed 2023-09-18T20:16:11Z
last_indexed 2023-09-18T20:16:11Z
_version_ 1777407802607665152

Similar Items