{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:10:24Z","timestamp":1726027824608},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030168407"},{"type":"electronic","value":"9783030168414"}],"license":[{"start":{"date-parts":[[2019,4,3]],"date-time":"2019-04-03T00:00:00Z","timestamp":1554249600000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-16841-4_20","type":"book-chapter","created":{"date-parts":[[2019,4,2]],"date-time":"2019-04-02T16:12:08Z","timestamp":1554221528000},"page":"186-195","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["$$F_{0}$$ F 0 Modeling Using DNN for Arabic Parametric Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Imene","family":"Zangar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zied","family":"Mnasri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Colotte","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":[[2019,4,3]]},"reference":[{"unstructured":"Pierrehumbert, J.: The phonology and phonetics of English intonation. Ph.D. Thesis, Massachusetts Institute of Technology (1980)","key":"20_CR1"},{"key":"20_CR2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511627743","volume-title":"A Perceptual Study of Intonation","author":"J Hart","year":"1990","unstructured":"Hart, J., Collier, R., Cohen, A.: A Perceptual Study of Intonation. Cambridge University Press, Cambridge (1990)"},{"unstructured":"Dusterhoff, K., Black, A.: Generating $$F_{0}$$ F 0 contour for speech synthesis using the tilt intonation theory. In: 3rd ESCA workshop on Intonation: Theory Models and Applications, pp. 107\u2013110. Athens, Greece (1997)","key":"20_CR3"},{"issue":"3","key":"20_CR4","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1121\/1.428453","volume":"107","author":"P Taylor","year":"2000","unstructured":"Taylor, P.: Analysis and synthesis of intonation using the tilt model. J. Acoust. Soc. Am. 107(3), 1697\u20131714 (2000)","journal-title":"J. Acoust. Soc. Am."},{"unstructured":"Moehler, G., Conkie, A.: Parametric modeling of Intonation using vector quantization. In: 3rd ESCA Workshop on Speech Synthesis, pp. 311\u2013316. Jenolan Caves, Australia (1998)","key":"20_CR5"},{"doi-asserted-by":"crossref","unstructured":"Wu, Z., Watts, O., King, S.: Merlin: An open source neural network speech synthesis system. In: 9th ISCA Workshop on Speech Synthesis, pp. 202\u2013207. Sunnyvale, USA (2016)","key":"20_CR6","DOI":"10.21437\/SSW.2016-33"},{"doi-asserted-by":"crossref","unstructured":"Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T. Kitamura, T.: Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In: 6th European Conference on Speech Communication and Technology, pp. 2347\u20132350. Budapest, Hungary (1999)","key":"20_CR7","DOI":"10.21437\/Eurospeech.1999-513"},{"doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: 38th International Conference on Acoustics, Speech, and Signal Processing, pp. 7962\u20137966. IEEE, Vancouver, Canada (2013)","key":"20_CR8","DOI":"10.1109\/ICASSP.2013.6639215"},{"doi-asserted-by":"crossref","unstructured":"Chen, B., Bian, T., Yu, K.: Discrete duration model for speech synthesis. In: 18th Annual Conference of the International Speech Communication Association, pp. 789\u2013793. Stockholm, Sweden (2017)","key":"20_CR9","DOI":"10.21437\/Interspeech.2017-1144"},{"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, pp. 597\u2013601. Poznan, Poland (2018)","key":"20_CR10","DOI":"10.21437\/SpeechProsody.2018-121"},{"unstructured":"Oord, A.V.D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., Kavukcuoglu, K.: Wavenet: a generative model for raw audio. arXiv preprint arXiv: 1609.03499 (2016)","key":"20_CR11"},{"unstructured":"Yoshimura, T.: Simultaneous modeling of phonetic and prosodic parameters, and characteristic conversion for HMM-based Text-to-Speech systems. Ph.D. Thesis, Department of Electrical and Computer Engineering, Nagoya Institute of Technology (2002)","key":"20_CR12"},{"doi-asserted-by":"crossref","unstructured":"Zen, H., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Hidden semi-Markov model based speech synthesis. In: 8th International Conference on Spoken Language Processing, pp. 1393\u20131396. Jeju Island, Korea (2004)","key":"20_CR13","DOI":"10.21437\/Interspeech.2004-460"},{"issue":"3","key":"20_CR14","first-page":"455","volume":"85","author":"K Tokuda","year":"2002","unstructured":"Tokuda, K., Masuko, T., Miyazaki, N., Kobayashi, T.: Multi-space probability distribution HMM. IEICE Trans. Inf. Syst. 85(3), 455\u2013464 (2002)","journal-title":"IEICE Trans. Inf. Syst."},{"doi-asserted-by":"publisher","unstructured":"Zen, H., Tokuda, K. Black, A.W.: Statistical parametric speech synthesis. In: Speech Communication 2009, vol. 51, pp. 1093\u20131064. ELSEVIER (2009). https:\/\/doi.org\/10.1016\/j.specom.2009.04.004","key":"20_CR15","DOI":"10.1016\/j.specom.2009.04.004"},{"issue":"5","key":"20_CR16","first-page":"1071","volume":"19","author":"K Yu","year":"2011","unstructured":"Yu, K., Young, S.: Continuous $$F_{0}$$ F 0 modeling for HMM based statistical parametric speech synthesis. IEICE Trans. Inf. Syst. 19(5), 1071\u20131079 (2011)","journal-title":"IEICE Trans. Inf. Syst."},{"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, pp. 1964\u20131968. Singapore (2014)","key":"20_CR17","DOI":"10.21437\/Interspeech.2014-443"},{"doi-asserted-by":"crossref","unstructured":"Chen, C.J., Gopinath, R.A., Monkowski, M.D., Picheny, M.A., Shen, K.: New methods in continuous Mandarin speech recognition. In: 5th European Conference on Speech Communication and Technology, pp. 1543\u20131546. Rhodes, Greece (1997)","key":"20_CR18","DOI":"10.21437\/Eurospeech.1997-444"},{"doi-asserted-by":"crossref","unstructured":"Chen, B., Lai, J., Yu, K.: Comparison of modeling target in LSTM-RNN duration model. In: 18th Annual Conference of the International Speech Communication Association, pp. 794\u2013798. Stockholm, Sweden (2017)","key":"20_CR19","DOI":"10.21437\/Interspeech.2017-1152"},{"unstructured":"Halabi, N., Wald, M.: Phonetic inventory for an Arabic speech corpus. In: 10th International Conference on Language Resources and Evaluation, pp. 734\u2013738. Slovenia (2016)","key":"20_CR20"},{"unstructured":"Speech Signal Processing Toolkit (SPTK). http:\/\/sp-tk.sourceforge.net\/","key":"20_CR21"},{"doi-asserted-by":"crossref","unstructured":"Houidhek, A., Colotte, V., Mnasri, Z., Jouvet, D.: DNN-based speech synthesis for Arabic: modelling and evaluation. In: 6th International Conference on Statistical Language and Speech Processing, pp. 9\u201320. Mons, Belgium (2018)","key":"20_CR22","DOI":"10.1007\/978-3-030-00810-9_2"},{"issue":"3","key":"20_CR23","doi-asserted-by":"publisher","first-page":"1638","DOI":"10.1121\/1.2951592","volume":"124","author":"A Camacho","year":"2008","unstructured":"Camacho, A., Harris, J.G.: A sawtooth waveform inspired pitch estimator for speech and music. J. Acoust. Soc. Am. 124(3), 1638\u20131652 (2008)","journal-title":"J. Acoust. Soc. Am."},{"unstructured":"Zen, H.: An example of context-dependent label format for HMM-based speech synthesis in English. The HTS CMUARCTIC demo (2006)","key":"20_CR24"}],"container-title":["Proceedings of the International Neural Networks Society","Recent Advances in Big Data and Deep Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-16841-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T02:53:30Z","timestamp":1663210410000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-16841-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,3]]},"ISBN":["9783030168407","9783030168414"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-16841-4_20","relation":{},"ISSN":["2661-8141","2661-815X"],"issn-type":[{"type":"print","value":"2661-8141"},{"type":"electronic","value":"2661-815X"}],"subject":[],"published":{"date-parts":[[2019,4,3]]},"assertion":[{"value":"3 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"INNSBDDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"INNS Big Data and Deep Learning conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sestri Levante","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"innsbddl2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/innsbddl2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}