The International Arab Journal of Information Technology (IAJIT)


Speech Synthesis System for the Holy Quran

This paper aims to develop a Text-To-Speech (TTS) synthesis system for the holly Quran recitation, to properly helps reciters and facilitates its use. In this work, the unit selection method is adopted and improved to reach a good speech quality. The proposed approach consists mainly of two steps. In the first one, an Expert System (ES) module is integrated by employing Arabic, Quran language, phonetic and phonological features. This part was considered as a preselection to optimize the synthesis algorithm's speed. The second step is the final selection of units by minimizing a concatenation cost function and a forward-backward dynamic programming search. The system is evaluated by native and non-native Arabic speakers. The results show that the goal of a correct Quran recitation by respecting its reading rules was reached, with 97 % of speech intelligibility and 72.13% of naturalness.

[1] Ahmed A., “ايجولونوف نآرقلا :ةسارد ماكحلأ ديوجتلا في ءوض ملع تاوصلأا ثيدحلا

[Quran Phonology: Quran Reciting Rules Based on Modern Acoustic],” MSc Thesis, Ain Chems University, 2004.

[2] Alías F., Formiga L., and Llorá X., “Efficient and Reliable Perceptual Weight Tuning for Unit- Selection Text-To-Speech Synthesis Based on Active Interactive Genetic Algorithms: A Proof- of-Concept,” Speech Communication, vol. 53, no. 5, pp. 786-800, 2011.

[3] Al-Radhi M., Abdo O., Csapó T., Abdou S., Németh G., and Fashal M., “A Continuous Vocoder for Statistical Parametric Speech Synthesis and its Evaluation Using an Audio- visual Phonetically Annotated Arabic Corpus,” Computer Speech and Language, vol. 60, 2020.

[4] Alsharif B., Tahboub R., and Arafeh L., “Arabic Text To Speech Synthesis Using Quran Based Natural Language Processing Module,” Journal of Theoretical and Applied Information Technology, vol. 83, no. 1, pp. 148-155, 2016.

[5] Amrouche A., Falek L., and Teffahi H., “Design and Implementation of a Diacritic Arabic Text- To-Speech System,” The International Arab Journal of Information Technology, vol. 14, no. 4, pp. 488-494, 2017.

[6] Bettayeb N., Guerti M., and Ramzan N., “A Forward-Backward Dynamic Programming Search for Arabic Unit Selection Speech Synthesis,” in Proceedings of 1st International Conference on Embedded and Distributed Systems, Oran, pp. 73-77, 2017.

[7] Bettayeb N. and Guerti M., “A Study to Build a Holy Quran Text-To-Speech System,” International Journal on Islamic Applications in Computer Science and Technology, vol. 7, no. 4, pp. 1-10, 2019.

[8] Dutoit T., Springer Handbook of Speech Processing, Springer Berlin Heidelberg, 2008.

[9] Elsayed E. and Fathy D., “Evaluation of Quran Recitation via OWL Ontology Based System,” The International Arab Journal of Information Technology, vol. 16, no. 6, pp. 970-977, 2019.

[10] Elshafei M., Al-Muhtaseb H., and Al-Ghamdi M., “Techniques for High Quality Arabic Speech Synthesis,” Information Sciences, vol. 140, no. 3, pp. 255-267, 2002.

[11] Fu R., Tao J., and Wen Z., “Progressive Neural Networks Based Features Prediction for The Target Cost in Unit-Selection Speech Synthesizer,” in Proceedings of 14th International Conference on Signal Processing, Beijing, pp. 504-509, 2018.

[12] Houidhek A., Colotte V., Mnasri Z., and Jouvet D., “DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation,” in Proceedings of 6th International Conference on Statistical Language and Speech Processing, Mons, pp. 9-20, 2018.

[13] Jongman A., Herd W., and Al‐Masri M., “Acoustic Correlates of Emphatic Consonants in Speech Synthesis System for the Holy Quran Recitation 15 Arabic,” The Journal of the Acoustical Society of America, vol. 121, no. 5, pp. 3169-3169, 2007.

[14] Kharb S., Kumar H., Kumar M., and Chaturvedi A., “Efficiency of a Machine Translation System,” in Proceedings of International Conference of Electronics, Communication and Aerospace Technology, Coimbatore, pp. 140-148, 2017.

[15] Narendra N. and Rao K., “Optimal Weight Tuning Method for Unit Selection Cost Functions in Syllable Based Text-To-Speech Synthesis,” Applied Soft Computing, vol. 13, no. 2, pp. 773- 781, 2013.

[16] Sweed A., “Islamway: the Quran Teacher,” Available from:فحصملا- ملعملا , Last Visited, 2019.

[17] Taylor P., Text-to-Speech Synthesis, Cambridge University Press, 2009.

[18] Tebbi H., Hamadouche M., and Azzoune H., “A New Hybrid Approach for Speech Synthesis: Application to the Arabic Language,” International Journal of Speech Technology, vol. 22, no. 4, pp. 629-637, 2018.

[19] “The Noble Quran,”, Last Visited, 2019.

[20] Zakariah M., Khan M., Tayan O., and Salah K., “Digital Quran Computing: Review, Classification, and Trend Analysis,” Arabian Journal for Science and Engineering, vol. 42, no. 8, pp. 3077-3102, 2017. Nadjla Bettayeb Ph.D student in the Electronics Department of the National Polytechnique school of Algiers, Algeria (ENP). She received her Engineer and Master degree in 2013 from the Electronics Department, ENP. Her current interests include Arabic and Holy Quran language processing and speech synthesis. Mhania Guerti Professor in the Signal and communication laboratory, Department of Electronics, National Polytechnique school of Algiers, Algeria (ENP). She received her MSc in 1984, from the ILP Algiers in collaboration with the CNET-Lannion (France). She got her Ph.D from ICP-INPG (Grenoble France), in 1993. She is specialized in Speech and Language Processing. Her main research interests include the areas of speech processing, acoustics, and audio-visual systems.