Decode Malay syllables: Cnn's key to Malay language understanding

Hashim, Nik Mohd Zarifie and Salleh, Azahari and Harun, Haleeda Norelham and Ahmad Azhar, Nursyahmina and Sulistiyo, Mahmud Dwi and Kamarudin, Atiqah Ilya (2024) Decode Malay syllables: Cnn's key to Malay language understanding. International Journal of Academic Research in Business and Social Sciences, 14 (10). pp. 480-492. ISSN 2222-6990

Text 01300211020241150351203.pdf Available under License Creative Commons Attribution. Download (609kB)

Abstract

Malay serves as the language of knowledge and is instrumental in educational settings, as exemplified by its significance in the Education Act of 1961. Furthermore, to support the government's initiatives in advancing the quality of education toward achieving global standards, there is a growing demand for innovative pedagogical methods in teaching the Malay language. In this context, numerous researchers have concentrated their efforts on developing speaker-independent systems, which find applications in language training, articulation therapy, and aiding language learners in mastering the intricacies of Malay phonetics, particularly focusing on vowels. Hence, the principal aim of this paper is primarily dedicated to the recognition of intelligently pronounced Malay syllables by distinct male and female groups, employing Neural Network technology. The primary objective of this research paper is to develop a robust system for the accurate recognition of Malay language syllables, which play a pivotal role in the context of the Malay language, widely used as the primary medium of communication in Malaysia. The implementation of this system leverages the Python programming language, known for its versatility and adaptability to various applications. The paper's primary focus lies in the careful observation and analysis of specific syllable components, particularly those involving the pronunciation of /a/, /e/, /i/, /o/, and /u/. These segments of the language pose particular challenges in terms of pronunciation, and the paper seeks to develop a comprehensive solution for their accurate recognition.

Item Type:	Article
Uncontrolled Keywords:	Audio signal processing, Convolutional neural networks (CNN), Natural language processing (NLP), Speech recognition, Spoken keyword spotting
Divisions:	Faculty Of Electronics And Computer Technology And Engineering
Depositing User:	Sabariah Ismail
Date Deposited:	11 Feb 2025 08:33
Last Modified:	11 Feb 2025 08:33
URI:	http://eprints.utem.edu.my/id/eprint/28214
Statistic Details:	View Download Statistic

Actions (login required)

View Item