{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:02:34Z","timestamp":1778346154199,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T00:00:00Z","timestamp":1598313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T00:00:00Z","timestamp":1598313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Signal, Image and Technology of Information Laboratory, Electrical engineering department"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s10772-020-09750-7","type":"journal-article","created":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T10:03:57Z","timestamp":1598349837000},"page":"569-584","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["DNN-based grapheme-to-phoneme conversion for Arabic text-to-speech synthesis"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7665-9141","authenticated-orcid":false,"given":"Ikbel","family":"Hadj Ali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8929-3609","authenticated-orcid":false,"given":"Zied","family":"Mnasri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zied","family":"Lachiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,25]]},"reference":[{"key":"9750_CR2","unstructured":"Abandah, G., & Arabiyat, A. et\u00a0al. (2017). Investigating hybrid approaches for Arabic text diacritization with recurrent neural networks. In 2017 IEEE Jordan conference on applied electrical engineering and computing technologies (AEECT) (pp. 1\u20136). IEEE"},{"issue":"2","key":"9750_CR1","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10032-015-0242-2","volume":"18","author":"GA Abandah","year":"2015","unstructured":"Abandah, G. A., Graves, A., Al-Shagoor, B., Arabiyat, A., Jamour, F., & Al-Taee, M. (2015). Automatic diacritization of Arabic text using recurrent neural networks. International Journal on Document Analysis and Recognition (IJDAR), 18(2), 183\u2013197.","journal-title":"International Journal on Document Analysis and Recognition (IJDAR)"},{"key":"9750_CR3","doi-asserted-by":"crossref","unstructured":"Abbad, H., & Xiong, S. (2020). Multi-components system for automatic arabic diacritization. In European conference on information retrieval (pp. 341\u2013355). Berlin: Springer.","DOI":"10.1007\/978-3-030-45439-5_23"},{"key":"9750_CR4","doi-asserted-by":"crossref","unstructured":"Abdelali, A., Darwish, K., Durrani, N., & Mubarak, H. (2016). Farasa: A fast and furious segmenter for Arabic. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Demonstrations (pp. 11\u201316).","DOI":"10.18653\/v1\/N16-3003"},{"key":"9750_CR5","doi-asserted-by":"crossref","unstructured":"Abdelmalek, R., & Mnasri, Z. (2016). High quality arabic text-to-speech synthesis using unit selection. In 2016 13th international multi-conference on systems, signals & devices (SSD) (pp. 1\u20135). IEEE","DOI":"10.1109\/SSD.2016.7473681"},{"key":"9750_CR6","first-page":"49","volume":"2018","author":"IH Ali","year":"2018","unstructured":"Ali, I. H., Mnasri, Z., & Lachiri, Z. (2018). Arabic character diacritization using DNN. ExLing, 2018, 49.","journal-title":"ExLing"},{"key":"9750_CR7","unstructured":"Arabic speech corpus. Retrieved 5 Mar 2020, from http:\/\/en.arabicspeechcorpus.com\/diacritiser.php."},{"key":"9750_CR8","volume-title":"Long short-term memory networks with python: Develop sequence prediction models with deep learning","author":"J Brownlee","year":"2017","unstructured":"Brownlee, J. (2017). Long short-term memory networks with python: Develop sequence prediction models with deep learning. Vermont: Machine Learning Mastery."},{"key":"9750_CR9","unstructured":"Buckwalter, T. (2002). Arabic transliteration. http:\/\/www.qamus.org\/transliteration.htm."},{"issue":"1","key":"9750_CR10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","volume":"40","author":"G Chandrashekar","year":"2014","unstructured":"Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16\u201328.","journal-title":"Computers & Electrical Engineering"},{"key":"9750_CR11","doi-asserted-by":"crossref","unstructured":"Darwish, K., Mubarak, H., & Abdelali, A. (2017). Arabic diacritization: Stats, rules, and hacks. In Proceedings of the third Arabic natural language processing workshop (pp. 9\u201317).","DOI":"10.18653\/v1\/W17-1302"},{"key":"9750_CR12","unstructured":"Elshafei, M., Al-Muhtaseb, H., & Alghamdi, M. (2006). Statistical methods for automatic diacritization of Arabic text. In The Saudi 18th national computer conference, Riyadh (Vol. 18, pp. 301\u2013306)."},{"key":"9750_CR13","doi-asserted-by":"crossref","unstructured":"Fadel, A., Tuffaha, I., & Al-Ayyoub M.et\u00a0al. (2019). Arabic text diacritization using deep neural networks. In 2019 2nd international conference on computer applications & information security (ICCAIS) (pp. 1\u20137). IEEE","DOI":"10.1109\/CAIS.2019.8769512"},{"key":"9750_CR14","unstructured":"Fukui, R. (2004). Tipa manual. http:\/\/www.ctan.org\/texarchive\/fonts\/tipa\/tipaman.pdf."},{"issue":"5\u20136","key":"9750_CR15","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Networks, 18(5\u20136), 602\u2013610.","journal-title":"Neural Networks"},{"key":"9750_CR16","doi-asserted-by":"crossref","unstructured":"Habash, N., & Rambow, O. (2007). Arabic diacritization through full morphological tagging. In Human language technologies 2007: The conference of the North American chapter of the association for computational linguistics; companion volume, short papers (pp. 53\u201356)","DOI":"10.3115\/1614108.1614122"},{"key":"9750_CR18","doi-asserted-by":"crossref","unstructured":"Houidhek, A., Colotte, V., Mnasri, Z., & Jouvet, D. (2018). DNN-based speech synthesis for arabic: modelling and evaluation. In International conference on statistical language and speech processing (pp. 9\u201320). Berlin: Springer","DOI":"10.1007\/978-3-030-00810-9_2"},{"key":"9750_CR17","doi-asserted-by":"crossref","unstructured":"Houidhek, A., Colotte, V., Mnasri, Z., Jouvet, D., & Zangar, I. (2017). Statistical modelling of speech units in hmm-based speech synthesis for arabic.","DOI":"10.1007\/s10772-018-09558-6"},{"key":"9750_CR19","doi-asserted-by":"crossref","unstructured":"Hunt, A.\u00a0J., & Black, A.\u00a0W. (1996). Unit selection in a concatenative speech synthesis system using a large speech database. In 1996 IEEE international conference on acoustics, speech, and signal processing conference proceedings (Vol.\u00a01, pp. 373\u2013376). IEEE","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"9750_CR20","unstructured":"Introduction to speech processing, CSE TAMU 2017. Retrieved 5 Mar 2020, from http:\/\/courses.cs.tamu.edu\/rgutier\/csce630_f17\/"},{"issue":"7553","key":"9750_CR21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436\u2013444.","journal-title":"Nature"},{"key":"9750_CR22","unstructured":"Maamouri, M., Bies, A., Buckwalter, T., & Mekki, W. (2004). The PENN Arabic treebank: Building a large-scale annotated Arabic corpus. In NEMLAR conference on Arabic language resources and tools, Cairo (Vol.\u00a027, pp. 466\u2013467)"},{"key":"9750_CR23","unstructured":"Mnasri, Z., Boukadida, F., & Ellouze, N. (2005). Analyse\/synth\u00e8se de parole par mod\u00e9lisation sinuso\u00efdale et recouvrement addition. In SETIT."},{"key":"9750_CR24","unstructured":"Onaolapo, J., Idachaba, F., Badejo, J., Odu, T., & Adu, O. (2014). A simplified overview of text-to-speech synthesis."},{"key":"9750_CR25","doi-asserted-by":"crossref","unstructured":"Rajouani, A., Najim, M., Chiadmi, D., & Zyoute, M. (1987). Synthesis-by-rule of arabic language. In European conference on speech technology.","DOI":"10.21437\/ECST.1987-8"},{"key":"9750_CR27","unstructured":"Rashwan, M., Al-Badrashiny, M., Attia, M., & Abdou, S. (2009). A hybrid system for automatic Arabic diacritization. In The 2nd international conference on Arabic language resources and tools (pp. 54\u201360)."},{"issue":"1","key":"9750_CR26","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1109\/TASL.2010.2045240","volume":"19","author":"MA Rashwan","year":"2010","unstructured":"Rashwan, M. A., Al-Badrashiny, M. A., Attia, M., Abdou, S. M., & Rafea, A. (2010). A stochastic Arabic diacritizer based on a hybrid of factorized and unfactorized textual features. IEEE Transactions on Audio, Speech, and Language Processing, 19(1), 166\u2013175.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9750_CR28","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.csl.2015.04.002","volume":"34","author":"I Rebai","year":"2015","unstructured":"Rebai, I., & BenAyed, Y. (2015). Text-to-speech synthesis system with arabic diacritic recognition system. Computer Speech & Language, 34(1), 43\u201360.","journal-title":"Computer Speech & Language"},{"key":"9750_CR29","unstructured":"Research Developement International (RDI). Retrieved 4 Aug 2010, from https:\/\/www.rdi-eg.com\/."},{"key":"9750_CR30","doi-asserted-by":"crossref","unstructured":"Roth, R., Rambow, O., Habash, N., Diab, M., & Rudin, C. (2008). Arabic morphological tagging, diacritization, and lemmatization using lexeme models and feature ranking. In Proceedings of ACL-08: HLT, short papers (pp. 117\u2013120).","DOI":"10.3115\/1557690.1557721"},{"key":"9750_CR31","unstructured":"Shamela Library. Retrieved 4 Aug 2010, from https:\/\/shamela.ws\/."},{"key":"9750_CR32","doi-asserted-by":"crossref","unstructured":"Shen, J., Pang, R., Weiss, R.\u00a0J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., & Skerrv-Ryan, R. et\u00a0al. (2018). Natural TTS synthesis by conditioning wavenet on MEL spectrogram predictions. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 4779\u20134783). IEEE","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"9750_CR33","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338","volume-title":"Text-to-speech synthesis","author":"P Taylor","year":"2009","unstructured":"Taylor, P. (2009). Text-to-speech synthesis. Cambridge: Cambridge University Press."},{"key":"9750_CR34","unstructured":"Test data. Retrieved 5 Mar 2020, from http:\/\/www.RDI-eg.com\/RDI\/TestData."},{"key":"9750_CR35","unstructured":"Tokuda, K., Zen, H., & Black, A.\u00a0W. (2002). An hmm-based speech synthesis system applied to english. In IEEE speech synthesis workshop (pp. 227\u2013230)."},{"key":"9750_CR36","unstructured":"Training data. Retrieved 5 Mar 2020, from http:\/\/www.RDI-eg.com\/RDI\/."},{"key":"9750_CR37","unstructured":"Wells, J.\u00a0C., Gibbon, D., Moore, R., & Winski, R. (1997). Handbook of standards and resources for spoken language systems. Mouton de Gruyter."},{"key":"9750_CR38","doi-asserted-by":"crossref","unstructured":"Zayyan, A.\u00a0A., Elmahdy, M., binti Husni, H., & Al\u00a0Ja\u2019am, J.\u00a0M. (2016). Automatic diacritics restoration for modern standard Arabic text. In 2016 IEEE symposium on computer applications & industrial electronics (ISCAIE) (pp. 221\u2013225). IEEE.","DOI":"10.1109\/ISCAIE.2016.7575067"},{"key":"9750_CR39","doi-asserted-by":"crossref","unstructured":"Ze, H., Senior, A., & Schuster, M. (2013). Statistical parametric speech synthesis using deep neural networks. In 2013 IEEE international conference on acoustics, speech and signal processing (pp. 7962\u20137966). IEEE","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"9750_CR40","unstructured":"Zen, H. (2006). An example of context-dependent label format for HMM-based speech synthesis in English, The HTS CMUARCTIC demo (Vol. 133)"},{"issue":"3","key":"9750_CR41","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.csl.2008.06.001","volume":"23","author":"I Zitouni","year":"2009","unstructured":"Zitouni, I., & Sarikaya, R. (2009). Arabic diacritic restoration approach based on maximum entropy models. Computer Speech & Language, 23(3), 257\u2013276.","journal-title":"Computer Speech & Language"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09750-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09750-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09750-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T13:03:45Z","timestamp":1723467825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09750-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,25]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["9750"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09750-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,25]]},"assertion":[{"value":"9 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}