The variability of speech patterns produced by individuals is unique. The uniqueness is due to the accent influenced by the individual’s native dialect. Modeling individual variation of spoken language is a challenge under the Automatic Speech Recognition (ASR) field. The individual differences concerning of accent revealed the critical issues in Classical Arabic (CA) recitation among Malay speakers. This problem is caused by the misarticulate phonemes, which affected by the Malay colloquial dialect and native language. Most of ASR researchers are unable to understand the behavior of phonemes and speech patterns in CA, thus degrading the ASR performance. This paper focuses on identifying the accent of Malay speakers on the recitation of Sūrah Al-Fātiḥah with 7 Quranic accents, using the proposed feature extraction technique. In this work, the technique presented is a combination of spectral and prosodic features, which are mainly designed for accent in ASR. Differed with current conventional method, where the spectral feature alone has been applied for feature extraction in many ASR research. The prosodic elements in CA such as pitch, energy and spectral-tilt need to be taken into consideration, thus a significant variety of features for each phoneme able to help in distinguishing one accent from another. Meanwhile, the spectral representation of Mel-Frequency Cepstral Coefficients (MFCC) is utilized for the decorrelating property of the cepstrum. At present, Gaussian Mixture Models (GMM) has been applied for the classification stage. From experimental results, the system performance is the best when the prosodic is integrated with MFCC, alongside the GMM with 81.7%-89.6% of accuracy. It was 5.5%-7.3% increment as compared to MFCC alone.
Research into Automatic Speech Recognition (asr) software for the Arabic language has gained significance in recent years. Since the Qurʾan is in Arabic, the rendering of it into Arabic asr may appear difficult and quite challenging. Furthermore, the way in which any Qurʾanic verse is recited can differ from one person to another, as can even the same āya (verse), as this is totally dependent on the reciters’ level of understanding of tajwīd (pronunciation rules while reading the recitation of the Qurʾan) while delivering the āya. In this paper, we provide a comprehensive review of the challenges for developing Qurʾanic verse recitation recognition software, focused on the tajwīd rules for checking features and language. Other related issues that fall under Qurʾanic linguistic aspects and properties, including recitation errors (common/possible mistakes made while reading) of passages, are also discussed in this paper. Further areas of potential expansion, new ideas, and new areas of research for supporting Qurʾanic learning for the Muslim community are also explored and identified. Thus, this paper will allow the field to be expanded and developed, all of which focusses on improving Qurʾanic learning process through a talaqqī and mushāfaha method of Qurʾan recitation.
Speech processing for Quranic Arabic has been carried out, and has been such an active field of research, since a few years ago. We propose in this paper, a review that focuses on the use and on the potential of automatic speech recognition (ASR) computer-based technology to supporting Quranic learning processes. Thus, the aspects of Computer-Aided Pronunciation Learning (CAPL) will be discussed, focus towards the implementation on Quranic learning of Al-Jabari method. We believe this method is a fast, efficient method of learning, as well as a practical way of learning Al-Quran using ICT tools. The advantages and drawbacks of CAPL systems towards the implementation in Quranic learning, as well as Al-Jabari method will be discussed in details.
Purpose -The purpose of this paper is to provide a structural overview of speech recognition system for developing Quranic verse recitation recognition with tajweed checking rules function. This function has been introduced, due to support the existing and manual method of talaqqi and musyafahah method in Quranic learning process, which described as face-to-face learning process between students and teachers. Here, the process of listening, correction and repetition of the correct Al-Quran recitation took place in real-time condition. However, this method is believed to become less effective and unattractive to be implemented, especially towards the young Muslim generation who are more attracted to the latest technology. Design/methodology/approach -This paper focuses on the development of software prototype, mainly for developing an automated Tajweed checking rules engine, purposely for Quranic learning. It has been implemented and tested towards the j-QAF students at primary school in Malaysia. Findings -The paper provides empirical insight about the viability and implementation of Mel-frequency cepstral coefficients (MFCC) algorithm of feature extraction technique and hidden Markov model (HMM) classification for recognition part, with the results of recognition rate reached to 91.95 percent (ayates) and 86.41 percent (phonemes), after been tested on sourate Al-Fatihah. Originality/value -Based on the result, proved that the engine has a potential to be used as an educational tool, which helps the students read Al-Quran better, even without the presence of teachers (Mudarris)/parents to monitor them. Automated system with Tajweed checking rules capability functions could be another alternative due to support the existing method of manual skills of Quranic learning process, without denying the main role of teachers in teaching Al-Quran.
Modeling individual's variation in speech pattern can be challenging in Automatic Speech Recognition (ASR). In Classical Arabic (CA) language, 20 Quranic accents are permitted for Quranic recitation. An ASR system for CA with accent detection requires a modeling method that can capture speech pattern changes. Here, we study the accentual influences on Malay speakers' pronunciation and its prosodic impacts towards ASR system for CA language with seven Quranic accents identification. The proposed ASR system was developed over three stages. First, a dataset of Surah Al-Fatihah recitation was recorded from 14 Malay speakers in seven Quranic accents, forming a total of 5,684 words. Second, various spectral and prosodic features are extracted from the dataset for further classification process. The final stage includes training and testing the classification model. The existing ASR systems are often enabled by Gaussian Mixture Models (GMM) because of its capability to represent a wide range of sample distributions. However, GMM is susceptible to overfitting when the model complexity is high, due to the presence of singularities. To support identification of seven Quranic accents, Universal Background Model (UBM) is adapted to GMM using Maximum A Posteriori (MAP) estimation method. The UBM models were trained over each of Quranic accents, and combined to establish final UBM with 512 mixture components. The proposed ASR system utilizing the GMM-UBM outperformed k-NN, GMM, and GMM-iVector in identifying Al-Fatihah recitation to the corresponding Quranic accents. The GMM-UBM yields a testing accuracy of 86.148%, which is an increment of 4.435% from utilizing GMM alone.INDEX TERMS Automatic speech recognition (ASR), Gaussian mixture model-universal background model (GMM-UBM), Malay speakers, Quranic accents
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.