{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:16:09Z","timestamp":1751948169744,"version":"3.41.2"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030008093"},{"type":"electronic","value":"9783030008109"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-00810-9_2","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T05:02:57Z","timestamp":1537246977000},"page":"9-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation"],"prefix":"10.1007","author":[{"given":"Amal","family":"Houidhek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Colotte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zied","family":"Mnasri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Jouvet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Abdou, S.M., Rashwan, M.: Improving Arabic HMM based speech synthesis quality. In: 9th International Conference on Spoken Language Processing, INTERSPEECH 2006, Pittsburgh, Pennsylvania (2006)","DOI":"10.21437\/Interspeech.2006-390"},{"key":"2_CR2","doi-asserted-by":"publisher","DOI":"10.1515\/9783110878769","volume-title":"Arabic Phonology: An Acoustical and Physiological Investigation","author":"SH Al-Ani","year":"1970","unstructured":"Al-Ani, S.H.: Arabic Phonology: An Acoustical and Physiological Investigation, vol. 61. Walter de Gruyter, Berlin (1970)"},{"issue":"1","key":"2_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio, Y.: Learning deep architectures for AI. Found. Trends\u00ae Mach. Learn. 2(1), 1\u2013127 (2009)","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Black, A.W., Zen, H., Tokuda, K.: Statistical parametric speech synthesis. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP 2007. vol. 4, pp. IV\u20131229. IEEE (2007)","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: 15th Annual Conference of the International Speech Communication Association, Singapore (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"key":"2_CR6","unstructured":"Halabi, N.: Modern standard Arabic speech corpus. Ph.D. thesis, University of Southampton (2015)"},{"key":"2_CR7","unstructured":"Houidhek, A., Colotte, V., Mnasri, Z., Jouvet, D., Zangar, I.: Statistical modelling of speech units in HMM-based speech synthesis for Arabic. In: 8th Language & Technology Conference, LTC 2017, Poznan, Poland (2017)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, ICASSP 1996, vol. 1, pp. 373\u2013376. IEEE, Atlanta (1996)","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"2_CR9","unstructured":"ITU: 800, methods for subjective determination of transmission quality. International Telecommunication Union (1996)"},{"key":"2_CR10","unstructured":"Jurafsky, D.: Speech and language processing: an introduction to natural language processing. In: Computational Linguistics, and Speech Recognition (2000)"},{"issue":"3","key":"2_CR11","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H Kawahara","year":"1999","unstructured":"Kawahara, H., Masuda-Katsuse, I., De Cheveigne, A.: Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds. Speech Commun. 27(3), 187\u2013207 (1999)","journal-title":"Speech Commun."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Khalil, K.M., Adnan, C.: Arabic HMM-based speech synthesis. In: International Conference on Electrical Engineering and Software Applications, ICEESA 2013, pp. 1\u20135. IEEE, Hammamet (2013)","DOI":"10.1109\/ICEESA.2013.6578437"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Krstulovic, S., Hunecke, A., Schr\u00f6der, M.: An HMM-based speech synthesis system applied to German and its adaptation to a limited set of expressive football announcements. In: 8th Annual Conference of the International Speech Communication Association, pp. 1897\u20131900. Citeseer, Antwerp (2007)","DOI":"10.21437\/Interspeech.2007-527"},{"key":"2_CR14","unstructured":"Maguer, S.L., Barbot, N., Boeffard, O.: Evaluation of contextual descriptors for HMM-based speech synthesis in French. In: 8th Workshop on Speech Synthesis, Barcelona, Spain (2013)"},{"issue":"7","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications. IEICE Trans. Inf. Syst. 99(7), 1877\u20131884 (2016)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"2_CR16","first-page":"65","volume":"100","author":"D Newman","year":"2002","unstructured":"Newman, D.: The phonetic status of Arabic within the world\u2019s languages: the uniqueness of the lughat al-daad. Antwerp Pap. Linguist. 100, 65\u201375 (2002)","journal-title":"Antwerp Pap. Linguist."},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Selouani, S.A., Caelen, J.: Arabic phonetic features recognition using modular connectionist architectures. In: Proceedings of the IEEE 4th Workshop on Interactive Voice Technology for Telecommunications Applications, IVTTA 1998, pp. 155\u2013160. IEEE, Torino (1998)","DOI":"10.1109\/IVTTA.1998.727712"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Tokuda, K., Zen, H., Black, A.W.: An HMM-based speech synthesis system applied to English. In: IEEE Speech Synthesis Workshop, Santa Monica, CA, USA, pp. 227\u2013230 (2002)","DOI":"10.1109\/WSS.2002.1224415"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Watts, O., Henter, G.E., Merritt, T., Wu, Z., King, S.: From HMMS to DNNs: where do the improvements come from? In: International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, pp. 5505\u20135509. IEEE, Lujiazui (2016)","DOI":"10.1109\/ICASSP.2016.7472730"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Wu, Z., Watts, O., King, S.: Merlin: an open source neural network speech synthesis system. In: Proceedings of the SSW, Sunnyvale, USA (2016)","DOI":"10.21437\/SSW.2016-33"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Zangar, I., Mnasri, Z., Colotte, V., Jouvet, D., Houidhek, A.: Duration modeling using DNN for Arabic speech synthesis. In: 9th International Conference on Speech Prosody, Poznan, Poland, pp. 597\u2013601 (2018)","DOI":"10.21437\/SpeechProsody.2018-121"},{"key":"2_CR22","unstructured":"Zen, H.: Deep learning in speech synthesis. In: SSW, Barcelona, Spain, p. 309 (2013)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, pp. 7962\u20137966. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639215"},{"issue":"5","key":"2_CR24","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1093\/ietisy\/e90-d.5.825","volume":"90","author":"H Zen","year":"2007","unstructured":"Zen, H., Tokuda, K., Masuko, T., Kobayasih, T., Kitamura, T.: A hidden semi-Markov model-based speech synthesis system. IEICE Trans. Inf. Syst. 90(5), 825\u2013834 (2007)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, M., Tao, J., Jia, H., Wang, X.: Improving HMM based speech synthesis by reducing over-smoothing problems. In: 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008, pp. 1\u20134. IEEE, Kunming (2008)","DOI":"10.1109\/CHINSL.2008.ECP.16"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00810-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:52:46Z","timestamp":1751910766000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-00810-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030008093","9783030008109"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00810-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mons","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/slsp2018.irdta.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"40","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3-4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}