Deep Learning Driven Arabic Text to Speech Synthesizer for Visually Challenged People

作     者：Mrim M.Alnfiai Nabil Almalki Fahd N.Al-Wesabi Mesfer Alduhayyem Anwer Mustafa Hilal Manar Ahmed Hamza 

作者机构：King Salman Center for Disability ResearchRiyadh13369Saudi Arabia Department of Information TechnologyCollege of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Special EducationCollege of EducationKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer ScienceCollege of Science&Arts at MuhayelKing Khaled UniversityAbha62217Saudi Arabia Department of Computer ScienceCollege of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversityAl-Aflaj16733Saudi Arabia Department of Computer and Self DevelopmentPreparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharj16242Saudi Arabia 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第36卷第6期

页      面：2639-2652页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 081202[工学-计算机软件与理论] 

基　　金：The authors extend their appreciation to the King Salman center for Disability Research for funding this work through Research Group no KSRG-2022-030 

主　　题：Saudi Arabia visually challenged people deep learning Aquila optimizer gated recurrent unit 

摘      要：Text-To-Speech(TTS)is a speech processing tool that is highly helpful for visually-challenged *** TTS tool is applied to transform the texts into human-like ***,it is highly challenging to accomplish the TTS out-comes for the non-diacritized text of the Arabic language since it has multiple unique features and *** special characters like gemination and diacritic signs that correspondingly indicate consonant doubling and short vowels greatly impact the precise pronunciation of the Arabic ***,such signs are not frequently used in the texts written in the Arabic language since its speakers and readers can guess them from the context *** this background,the current research article introduces an Optimal Deep Learning-driven Arab Text-to-Speech Synthesizer(ODLD-ATSS)model to help the visually-challenged people in the Kingdom of Saudi *** prime aim of the presented ODLD-ATSS model is to convert the text into speech signals for visually-challenged *** attain this,the presented ODLD-ATSS model initially designs a Gated Recurrent Unit(GRU)-based prediction model for diacritic and gemination ***,the Buckwalter code is utilized to capture,store and display the Arabic *** improve the TSS performance of the GRU method,the Aquila Optimization Algorithm(AOA)is used,which shows the novelty of the *** illustrate the enhanced performance of the proposed ODLD-ATSS model,further experi-mental analyses were *** proposed model achieved a maximum accu-racy of 96.35%,and the experimental outcomes infer the improved performance of the proposed ODLD-ATSS model over other DL-based TSS models.