A systematic approach for Malay language dialect identification by using CNN / Mohd Azman Hanif Sulaiman … [et al.]

Sulaiman, Mohd Azman Hanif and Abd Aziz, Nurhakimah and Zabidi, Azlee and Jantan, Zuraidah and Mohd Yassin, Ihsan and Megat Ali, Megat Syahirul Amin and Eskandari, Farzad (2021) A systematic approach for Malay language dialect identification by using CNN / Mohd Azman Hanif Sulaiman … [et al.]. Journal of Electrical and Electronic Systems Research (JEESR), 19: 13. pp. 25-37. ISSN 1985-5389

Abstract

As Malaysia moves forward towards the Industrial Revolution (IR 4. 0), computer systems have become part of everyday life, leading to increased man-machine interactions. Verbal communication is a convenient means to interact with computers. Speech recognition systems need to be robust to cater for various languages and dialects in order to interact better with humans. Dialects within a spoken language present a challenge for computers require a speech recognition system to translate these verbal commands to computer understanding of the underlying meaning from spoken words. In this paper, works on Malay language dialect identification are presented using Convolution Neural Network (CNN) trained on Mel Frequency Cepstral Coefficient (MFCC) features. Data was collected from 12 native speakers. Each speaker was instructed to utter 10 carefully selected words to emphasize the dialect nuances of the eastern, northern and central (standard) Malay dialect. The MFCC features were then extracted from the recorded audio samples and converted to graphical form. The images were then used to train a custom CNN neural network to differentiate between the various spoken words and their dialects. Results demonstrate that CNN was able to effectively differentiate between the spoken words with excellent accuracy (between 85% and 100%).

Metadata

Item Type: Article
Creators:
Creators
Email / ID Num.
Sulaiman, Mohd Azman Hanif
UNSPECIFIED
Abd Aziz, Nurhakimah
UNSPECIFIED
Zabidi, Azlee
UNSPECIFIED
Jantan, Zuraidah
UNSPECIFIED
Mohd Yassin, Ihsan
UNSPECIFIED
Megat Ali, Megat Syahirul Amin
UNSPECIFIED
Eskandari, Farzad
UNSPECIFIED
Subjects: T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electric apparatus and materials. Electric circuits. Electric networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Scanning systems
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Electrical Engineering
Journal or Publication Title: Journal of Electrical and Electronic Systems Research (JEESR)
UiTM Journal Collections: UiTM Journal > Journal of Electrical and Electronic Systems Research (JEESR)
ISSN: 1985-5389
Volume: 19
Page Range: pp. 25-37
Keywords: Convolution Neural Network, Mel Frequency Cepstrum Coefficient, speech recognition
Date: October 2021
URI: https://ir.uitm.edu.my/id/eprint/52057
Edit Item
Edit Item

Download

[thumbnail of 52057.pdf] Text
52057.pdf

Download (2MB)

ID Number

52057

Indexing

Statistic

Statistic details