{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:44:19Z","timestamp":1760255059197,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_5","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:15Z","timestamp":1760253555000},"page":"67-82","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effectiveness of Tacotron2 for Intonation Model Synthesis in Russian"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7934-6427","authenticated-orcid":false,"given":"Anastasiia","family":"Sherban","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1792-6064","authenticated-orcid":false,"given":"Uliana","family":"Kochetkova","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Black, A.W., Taylor P.: CHATR: A Generic Speech Synthesis System. COLING94. Japan, pp. 983\u2013986 (1994)","DOI":"10.3115\/991250.991307"},{"key":"5_CR2","unstructured":"Boersma, P., Heuven, V.: Speak and unSpeak with PRAAT. Glot International 5(9\/10), 341\u2013347 (2001)"},{"key":"5_CR3","volume-title":"Russkaja grammatika (Russian grammar)","author":"EA Bryzgunova","year":"1980","unstructured":"Bryzgunova, E.A.: Russkaja grammatika (Russian grammar). Nauka, Moscow (1980). (in Russian)"},{"key":"5_CR4","volume-title":"Zvuki i intonacii russkoj rechi (Sounds and intonations of Russian speech)","author":"EA Bryzgunova","year":"1981","unstructured":"Bryzgunova, E.A.: Zvuki i intonacii russkoj rechi (Sounds and intonations of Russian speech). Russkij jazyk, Moscow (1981). (in Russian)"},{"key":"5_CR5","unstructured":"Estebas-Vilaplana, E.: TL_ToBI: a new system for teaching and learning intonation. Phonetics Teaching and Learning Conference, pp. 39\u201342 (2013)"},{"key":"5_CR6","unstructured":"Dusterhoff, K., Black, A.: Generating F0 contours for speech synthesis using the Tilt intonation theory. In: Proceedings of the Intonation: Theories, Models and Applications, pp. 107\u2013110 (1997)"},{"key":"5_CR7","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1250\/ast.5.233","volume":"5","author":"H Fujisaki","year":"1984","unstructured":"Fujisaki, H., Hirose, K.: Analysis of voice fundamental frequency contours for declarative sentences of Japanese. J. Acoust. Soc. Japan 5, 233\u2013242 (1984)","journal-title":"J. Acoust. Soc. Japan"},{"key":"5_CR8","unstructured":"Foneticheskie Kharakteristiki Ironii (Phonetic Properties of Irony). In: Skrelin, P., Kochetkova, U. (ed.). Saint Peterburg University Publishing, Saint Petersburg, 170 p. (2025)"},{"key":"5_CR9","unstructured":"Harini, S., Manoj, G.: Text to Speech Synthesis (2024). https:\/\/arxiv.org\/pdf\/2401.13891. Accessed 25 Jan 2024"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Klatt, D.H.: Review of text-to-speech conversion for English. J. Acous. Soc. Amer. (82), 737\u2013793 (1987)","DOI":"10.1121\/1.395275"},{"key":"5_CR11","unstructured":"Kong, J., et al.: HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. arXiv preprint arXiv:2010.0564"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Korotkova, Y., Kalinovskiy, I., Vakhrusheva, T.: Word-level Text Markup for Prosody Control in Speech Synthesis, Interspeech (715), 2280\u20132284 (2024)","DOI":"10.21437\/Interspeech.2024-715"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Ling, Z.: Deep learning for acoustic modeling in parametric speech generation: a systematic review of existing techniques and future trends. Signal Process. Magaz. 32(3), 35\u201352","DOI":"10.1109\/MSP.2014.2359987"},{"key":"5_CR14","unstructured":"Lobanov, B.: History and Development of Speech Science and Technology in USSR, United Institut of Informatics Problems, Minsk, Belarus (2015)"},{"key":"5_CR15","first-page":"431","volume":"34","author":"C Od\u00e9","year":"2008","unstructured":"Od\u00e9, C.: Transcription of Russian intonation, ToRi, an interactive research tool and learning module on the internet. Stud. Slavic General Linguist. 34, 431\u2013448 (2008)","journal-title":"Stud. Slavic General Linguist."},{"key":"5_CR16","unstructured":"Od\u00e9, C.: Developing a Transcription of Russian Intonation (ToRI) (2004). fon.hum.uva.nl\/archive\/2003\/icphs\/OdeICPhS2003.pdf. Accessed 18 May 2025"},{"key":"5_CR17","unstructured":"Safonova, A.A.: Speech generation model for the Russian language with the possibility of prosody control: a master dissertation\/A.A. Safonova; Higher School of Economics, Moscow (2022)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Shen, J., Pang, R.: Natural TTS synthesis by conditioning WaveNet jn mel-spectrogram predictions (2018). https:\/\/arxiv.org\/pdf\/1712.05884. Accessed 16 Feb 2018","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"9","DOI":"10.4324\/9780429056253-2","volume":"1","author":"BH Story","year":"2019","unstructured":"Story, B.H.: History of Speech Synthesis. The Routledge Handbook of Phonetics, 1, 9\u201332 (2019)","journal-title":"The Routledge Handbook of Phonetics,"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Taylor, P.: Text-to-Speech Synthesis University of Cambridge, Cambridge, UK (2009)","DOI":"10.1017\/CBO9780511816338"},{"issue":"1","key":"5_CR21","first-page":"169","volume":"52","author":"J Volk","year":"2012","unstructured":"Volk, J.: Using the ToBi transcription to record the intonation of Slovene. University of Primorska 52(1), 169\u2013186 (2012)","journal-title":"University of Primorska"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Volskaya, N., Kachkovskaia T.: Prosodic annotation in the new corpus of Russian spontaneous speech CoRuSS. In: Proceedings of Speech Prosody (2016)","DOI":"10.21437\/SpeechProsody.2016-188"},{"key":"5_CR23","unstructured":"Volskaya, N.B., Skrelin, A.: Prosodic model for Russian. In: Vainio, M., Aulanko, R., Aaltonen, O. (eds.) Nordic Prosody: Proceedings of the Xth Conference, Helsinki 2008. Frankfurt am Main: Peter Lang (2008)"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y.: Tacotron: Towards end-to-end speech synthesis (2017). arXiv preprint arXiv:1703.10135","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Zen, H., Sak, H.: Unidirectional Long-Short-Term-Memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: International Conference on Acoustics, Speech and Signal Processing, no. 74, pp. 4470\u20134474 (2015)","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"5_CR26","first-page":"22","volume":"7","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Wang, J.: QI-TTS: questioning intonation control for emotional speech synthesis. Univ. Sci. Technol. China 7, 22\u201325 (2023)","journal-title":"Univ. Sci. Technol. China"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:20Z","timestamp":1760253560000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}