MFCC-VQ Approach For QalqalahTajweed Rule Checking

Malaysian Journal of Computer Science

Noorzaily Mohamed Noor¹  Zaidi Razak¹  Mohd Yamani Idna Idris¹  Zulkifli Mohd¹  Ahsiah Ismail¹ 

关键词: Speech Recognition;    Tajweed Recognition;    MFCC;    VQ;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: University of Malaya * Faculty of Computer Science and Information Technology

【 摘 要 】

In this paper, we investigate the speech recognition system for Tajweed Rule Checking Tool. We propose anovel Mel-Frequency Cepstral Coefficient andVector Quantization (MFCC-VQ) hybridalgorithm to helpstudents to learn and revise proper Al-Quran recitation by themselves. We describe a hybridMFCC-VQarchitecture toautomatically point out the mismatch between the students’recitationsandthecorrectrecitationverified by the expert. The vectoralgorithm is chosen due to its data reduction capabilities andcomputationally efficient characteristics.We illustrate our component model and describe the MFCC-VQproceduretodevelop theTajweed Rule CheckingTool.Two features, i.e., a hybrid algorithm and solely Mel-Frequency Cepstral Coefficientare compared to investigate their effect on the Tajweed RuleCheckingToolperformance. Experiments arecarried out on a dataset to demonstrate that the speed performanceof a hybrid MFCC-VQis86.928%, 94.495% and 64.683% faster than theMel-FrequencyCepstral Coefficient formale, female and children respectively.

【 授权许可】

Unknown