Reference Hub

This research has been cited in:

Chapter
The Baseline SystemCross-Word Modeling for Arabic Speech Recognition10.1007/978-1-4614-1213-7_3
Article
Building CMU Sphinx language model for the Holy Quran using simplified Arabic phonemesEgyptian Informatics Journal10.1016/j.eij.2016.04.002
Article
The Challenges of Developing a Living Arabic Phonetic Dictionary for Speech Recognition System: A Literature ReviewAdvanced Journal of Social Science10.21467/ajss.8.1.164-170
Article
Cross-word Arabic pronunciation variation modeling for speech recognitionInternational Journal of Speech Technology10.1007/s10772-011-9098-0
Conference
New birth of the Arabic phonetic dictionary2016 International Conference on Engineering & MIS (ICEMIS)10.1109/ICEMIS.2016.7745322
Article
Within-word pronunciation variation modeling for Arabic ASRs: a direct data-driven approachInternational Journal of Speech Technology10.1007/s10772-011-9122-4
Conference
Arabic Automatic Speech Recognition Enhancement2017 Palestinian International Conference on Information and Communication Technology (PICICT)10.1109/PICICT.2017.12
Article
Toward enhanced Arabic speech recognition using part of speech taggingInternational Journal of Speech Technology10.1007/s10772-011-9121-5
Article
Towards Deep Object Detection Techniques for Phoneme RecognitionIEEE Access10.1109/ACCESS.2020.2980452
Article
Educational System for the Holy Quran and Its Sciences for Blind and Handicapped People Based on Google Speech APIJournal of Software Engineering and Applications10.4236/jsea.2014.73017
Chapter
Study for Automatic Classification of Arabic Spoken DocumentsComputational Collective Intelligence10.1007/978-3-319-67077-5_44
Chapter
Part of Speech Tagging Approach to Designing Compound Words for Arabic Continuous Speech Recognition SystemsInformatics Engineering and Information Science10.1007/978-3-642-25483-3_27
Article
Synopsis on Arabic speech recognitionAin Shams Engineering Journal10.1016/j.asej.2021.06.020
Chapter
Cross-Word Pronunciation VariationsCross-Word Modeling for Arabic Speech Recognition10.1007/978-1-4614-1213-7_4
Chapter
ComputerAutomatic Robust Rule-Based Phonetization of Standard ArabicText, Speech, and Dialogue10.1007/978-3-319-24033-6_50
Article
Arabic phonemes recognition using hybrid LVQ/HMM model for continuous speech recognitionInternational Journal of Speech Technology10.1007/s10772-016-9337-5
Article
The impact of phonological rules on Arabic speech recognitionInternational Journal of Speech Technology10.1007/s10772-017-9440-2

Arabic Phonetic Dictionaries for Speech Recognition

Mohamed Ali, Moustafa Elshafei, Mansour Al-Ghamdi, Husni Al-Muhtaseb

Source Title: Journal of Information Technology Research (JITR)2(4)

Cite Article Cite Article

MLA

Ali, Mohamed, et al. "Arabic Phonetic Dictionaries for Speech Recognition." JITR vol.2, no.4 2009: pp.67-80. http://doi.org/10.4018/jitr.2009062905

APA

Ali, M., Elshafei, M., Al-Ghamdi, M., & Al-Muhtaseb, H. (2009). Arabic Phonetic Dictionaries for Speech Recognition. Journal of Information Technology Research (JITR), 2(4), 67-80. http://doi.org/10.4018/jitr.2009062905

Chicago

Ali, Mohamed, et al. "Arabic Phonetic Dictionaries for Speech Recognition," Journal of Information Technology Research (JITR) 2, no.4: 67-80. http://doi.org/10.4018/jitr.2009062905

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Phonetic dictionaries are essential components of large-vocabulary speaker-independent speech recognition systems. This paper presents a rule-based technique to generate phonetic dictionaries for a large vocabulary Arabic speech recognition system. The system used conventional Arabic pronunciation rules, common pronunciation rules of Modern Standard Arabic, as well as some common dialectal cases. The paper gives in detail an explanation of these rules as well as their formal mathematical presentation. The rules were used to generate a dictionary for a 5.4 hour corpus of broadcast news. The rules and the phone set were tested and evaluated on an Arabic speech recognition system. The system was trained on 4.3 hours of the 5.4 hours of Arabic broadcast news corpus and tested on the remaining 1.1 hours. The phonetic dictionary contains 23,841 definitions corresponding to about 14232 words. The language model contains both bi-grams and tri-grams. The Word Error Rate (WER) came to 9.0%.

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.

Username or email:

Password:

Forgot individual login password?

Create individual account

Arabic Phonetic Dictionaries for Speech Recognition

MLA

APA

Chicago

Export Reference

Abstract

Request Access