{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:02:19Z","timestamp":1778346139829,"version":"3.51.4"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,5,18]],"date-time":"2016-05-18T00:00:00Z","timestamp":1463529600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1007\/s10772-016-9342-8","type":"journal-article","created":{"date-parts":[[2016,5,18]],"date-time":"2016-05-18T13:05:43Z","timestamp":1463576743000},"page":"485-494","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Arabic speech synthesis and diacritic recognition"],"prefix":"10.1007","volume":"19","author":[{"given":"Ilyes","family":"Rebai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yassine","family":"BenAyed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,5,18]]},"reference":[{"key":"9342_CR1","doi-asserted-by":"crossref","first-page":"207","DOI":"10.3844\/jcssp.2009.207.213","volume":"5","author":"G Al-Said","year":"2009","unstructured":"Al-Said, G., & Abdallah, M. (2009). An Arabic text-to-speech system based on artificial neural networks. Journal of Computer Science, 5, 207\u2013213.","journal-title":"Journal of Computer Science"},{"key":"9342_CR2","first-page":"125","volume":"35","author":"M Alghamdi","year":"2010","unstructured":"Alghamdi, M., Zeeshan, M., & Hazim, A. (2010). Automatic restoration of Arabic diacritics: A simple, purely statistical approach. The Arabian Journal for Science and Engineering, 35, 125\u2013135.","journal-title":"The Arabian Journal for Science and Engineering"},{"key":"9342_CR3","unstructured":"Attia, M. (2005). Theory and implementation of a large-scale Arabic phonetic transcriptor, and applications. PhD thesis, Department of Electronics and Electrical Communications, Faculty of Engineering, Cairo."},{"key":"9342_CR4","unstructured":"Badrashiny, M, (2009). Automatic diacritizer for Arabic texts. PhD thesis, University of Cairo, Cairo"},{"key":"9342_CR5","doi-asserted-by":"crossref","unstructured":"Ben Sassi, S., Braham, R., & Belghith, A. (2001). Neural speech synthesis system for Arabic language using CELP algorithm. In ACS\/IEEE International Conference on Computer Systems and Applications (pp. 119\u2013121)","DOI":"10.1109\/AICCSA.2001.933962"},{"key":"9342_CR6","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s11760-007-0038-z","volume":"2","author":"F Chouireb","year":"2008","unstructured":"Chouireb, F., & Guerti, M. (2008). Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model. Signal, Image and Video Processing, 2, 73\u201387.","journal-title":"Signal, Image and Video Processing"},{"key":"9342_CR7","unstructured":"Ciresan, D., Meier, U., Masci, J., Gambardella, L., & Schmidhuber, J. (2011). High-performance neural networks for visual object classification. Computing Research Repository abs\/1102.0183:1\u201311"},{"key":"9342_CR8","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/S0020-0255(01)00175-X","volume":"140","author":"M Elshafei","year":"2002","unstructured":"Elshafei, M., Al-Muhtaseb, H., & Al-Ghamdi, M. (2002). Techniques for high quality Arabic speech synthesis. Information Sciences, 140, 255\u2013267.","journal-title":"Information Sciences"},{"key":"9342_CR9","unstructured":"Elshafei, M., Almuhtasib, H., & Alghamdi, M. (2006). Machine generation of Arabic diacritical marks. In The 2006 World Congress in Computer Science Computer Engineering, and Applied Computing, pp. 128\u2013133."},{"key":"9342_CR10","doi-asserted-by":"crossref","unstructured":"Fares, T., Khalil, A., & Hegazy, A. (2008). Usage of the HMM-based speech synthesis for intelligent Arabic voice. In International Conference on Computers and Their Applications (pp. 93\u201398).","DOI":"10.1063\/1.2953060"},{"key":"9342_CR11","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1109\/TCSI.2003.818614","volume":"50","author":"M Forti","year":"2003","unstructured":"Forti, M., & Nistri, P. (2003). Global convergence of neural networks with discontinuous neuron activations. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 50, 1421\u20131435.","journal-title":"IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications"},{"key":"9342_CR12","doi-asserted-by":"crossref","unstructured":"Hamad, M., & Hussain, M. (2011). Arabic text-to-speech synthesizer. In IEEE Student Conference on Research and Development (pp. 409\u2013414).","DOI":"10.1109\/SCOReD.2011.6148774"},{"key":"9342_CR13","unstructured":"Harrat, S., Meftouh, K., Abbas, M., & Smaili, K. (2014). Grapheme to phoneme conversion: An Arabic dialect case. In ISCA Tutorial and Research Workshop on Non Linear Speech Processing (pp. 1\u20136)."},{"key":"9342_CR14","first-page":"49","volume":"7","author":"S Imai","year":"2007","unstructured":"Imai, S., Sumita, K., & Furuichi, C. (2007). Investigating an Arabic text to speech system based on diphone concatenation. International Journal of Intelligent Computing and Information Sciences, 7, 49\u201369.","journal-title":"International Journal of Intelligent Computing and Information Sciences"},{"key":"9342_CR15","unstructured":"Kantabutra, V. (2006). Towards reliable convergence in the training of neural networks\u2014the streamlined glide algorithm and the LM Glide algorithm. In International Conference on Machine Learning: Models, Technologies and Applications (pp. 80\u201387)."},{"key":"9342_CR16","doi-asserted-by":"crossref","unstructured":"Khalil, K., & Adnan, C. (2013). Arabic HMM-based speech synthesis. In International Conference on Electrical Engineering and Software Applications (pp. 1\u20135).","DOI":"10.1109\/ICEESA.2013.6578437"},{"key":"9342_CR17","doi-asserted-by":"crossref","first-page":"124","DOI":"10.4236\/jsea.2012.512B024","volume":"5","author":"M Khorsheed","year":"2012","unstructured":"Khorsheed, M. (2012). A HMM-based system to diacritize Arabic text. Journal of Software Engineering and Applications, 5, 124\u2013127.","journal-title":"Journal of Software Engineering and Applications"},{"key":"9342_CR18","unstructured":"Kominek, J., Schultz., T., & Black, A. (2008). Synthesizer voice quality of new languages calibrated with mean Mel Cepstral Distortion. In Workshop on Spoken Language Technologies for Under-Resourced Languages (pp. 1\u20136)."},{"key":"9342_CR19","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Image Net classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (pp. 1097\u20131105)."},{"key":"9342_CR20","unstructured":"Martin, K., Grezl, F., Hannemann, M., Vesely, K., & Cernocky, J. (2013). BUT BABEL system for spontaneous Cantonese. In Interspeech (pp. 2589\u20132593)."},{"key":"9342_CR21","first-page":"352","volume":"4","author":"Z Mnasri","year":"2010","unstructured":"Mnasri, Z., Boukadida, F., & Ellouze, N. (2010). F0 contour modeling for Arabic text-to-speech synthesis using Fujisaki parameters and neural networks. Signal Processing: An International Journal, 4, 352\u2013369.","journal-title":"Signal Processing: An International Journal"},{"key":"9342_CR22","doi-asserted-by":"crossref","unstructured":"Raghavendra, E., Vijayaditya, P., & Prahallad, K. (2010). Speech synthesis using artificial neural networks. In National Conference on Communications (pp. 1\u20135).","DOI":"10.1109\/NCC.2010.5430190"},{"key":"9342_CR23","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1109\/TASL.2010.2045239","volume":"19","author":"T Raitio","year":"2011","unstructured":"Raitio, T., Suni, A., Yamagishi, J., Pulakka, H., Nurminen, J., & Vainio, M., et al. (2011). Hmm-based speech synthesis utilizing glottal inverse filtering. IEEE Transactions on Audio, Speech, and Language Processing, 19, 153\u2013165.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9342_CR24","doi-asserted-by":"crossref","unstructured":"Rebai, I., & BenAyed, Y. (2013). Arabic text to speech synthesis based on neural networks for MFCC estimation. In International Conference on Artificial Intelligence (pp. 1\u20135).","DOI":"10.1109\/WCCIT.2013.6618665"},{"key":"9342_CR25","unstructured":"Vinyals, O., Jia, Y., Deng, L., & Darrell, T. (2012). Learning with recursive perceptual representations. In 26th Annual Conference on Neural Information Processing Systems 2012 (pp. 2834\u20132842)."},{"key":"9342_CR26","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/S0885-2308(03)00035-4","volume":"18","author":"A Yousif","year":"2004","unstructured":"Yousif, A. (2004). Phonetization of Arabic: Rules and algorithms. Computer Speech and Language, 18, 339\u2013373.","journal-title":"Computer Speech and Language"},{"key":"9342_CR27","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., & Schuster, M. (2013). Statistical parametric speech synthesis using deep neural networks. In International Conference on Acoustics, Speech, and Signal Processing (pp. 7962\u20137966).","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"9342_CR28","doi-asserted-by":"crossref","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 and Language, 23, 257\u2013276.","journal-title":"Computer Speech and Language"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9342-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9342-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9342-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:43:05Z","timestamp":1692344585000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9342-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,18]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,9]]}},"alternative-id":["9342"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9342-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,18]]}}}