International Journal Of Interactive Digital Media, Vol. 4(2), ISSN 2289-4098, e-ISSN 2289-4101 www.ijidm.org 13 © 2016 International Journal of Interactive Digital Media Malay Word Pronunciation Test Application for Pre-School Children M.Y. Shahrul Azmi, Abstract—In Malaysia, many researchers focus on developing independent speaker speech recognition systems that uses Malay Language. Accuracy, noise robustness and processing time are concerns when developing speech therapy systems especially for children. In this study, a Malay word pronunciation test application is developed using Spectrum Delta features and Logistic Regression classification model in an effort to improve Malay word pronunciation for pre-school children aged between 3-6 years old. Results showed that the pronunciation application can assist children to test and improve their Malay word pronunciation. Index Terms—Malay Word, Pronunciation Test, Pre-School Children ——————————  —————————— 1 INTRODUCTION omputer based speech therapy and assessment is still new in Malaysia. In Bahasa Malaysia language, children are normally taught to spell Malay words using a combination of consonant and vowel sounds such as “BACA” represented by syllable “BA” and “CA”. Speech therapy that uses vowel phonemes can be used to improve Malay word pronunciation for children. A hearing impaired person can be trained to speak properly with a good degree of intelligibility in pronouncing words. A high degree of standard Malay vowel recognition capability is needed in all of these systems. Although there are many studies on Malay phoneme recognition, more work still needs to be done. Most of these studies use multiple frame analysis. Accuracy, noise robustness and processing time are still concerns when developing speech therapy systems, especially for children using Malay Language. The accuracy aspect involves factors such as age and gender. The size of the vocal tract of children of different gender and age varies which causes their voice to have different fundamental frequencies. Any application that uses vowel phonemes requires a high degree of Standard Malay (SM) vowel recognition capability. This motivates this study to have an objective of developing a Malay word pronunciation test application in an effort to improve Malay word pronunciation for pre- school children aged between 3-6 years old. 2 MALAY SPEECH THERAPY SYSTEMS A Computer-based Malay Language Articulation Diagnostic System was developed using Hidden Markov Model (HMM) and Mel-Frequency Cepstral Coefficients (MFCCs) [1]. It was developed using a database of Malay words. In 2012, Tan et.al developed a Malay dialect translation and synthesis system, but still at a preliminary stage [2]. The speech synthesis system used here is an HMM speech synthesis system (HTS Speech Synthesis System) at a sampling rate of 22 kHz. The results were promising, but the system does not test on pronunciation. A research was done in 2014 with the objective of developing an ASR system for Malay-speaking children [3]. The speech corpus comprises of six children uttering a total of 390 sentences. The parameter training is performed using the HTK toolkit by utilizing an HMM speech acoustic model of Malay-speaking children. The system can accurately recognize of up to 76% of test words. Yusof et.al did a study about speech intelligibility of deaf children in Malaysia using a Malay Speech Intelligibility Test (MSIT) system [4]. Researchers from Universiti Malaysia Sarawak did a study on syllabification algorithm based on Malay syllable structure [5]. It was used to build the Iban and Bidayuh syllable list and speech corpus. The accuracy, using Categorical Estimation (CE), gave a mean score of 3.07 out of 5. 3 MALAY WORD PRONUNCIATION APPLICATION 2.1 Speech Recognition Engine The Malay Word Pronunciation Application engine is based on vowel recognition process. It started with the data acquisition, followed by filtering and pre-processing, frame selection, speech signal modelling, feature extraction and vowel recognition processes as shown in Fig.1. ———————————————— • M.Y. Shahrul Azmi is with the UUM Technopreneur Incubation Center Universiti Utara Malaysia, Malaysia, Kedah 06010. E-mail: shahrulazmi@uum.edu.my C brought to you by CORE View metadata, citation and similar papers at core.ac.uk provided by UUM Repository