{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:09:54Z","timestamp":1777450194529,"version":"3.51.4"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030279462","type":"print"},{"value":"9783030279479","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-27947-9_26","type":"book-chapter","created":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T23:02:43Z","timestamp":1567378963000},"page":"307-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Czech Speech Synthesis with Generative Neural Vocoder"],"prefix":"10.1007","author":[{"given":"Jakub","family":"V\u00edt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zden\u011bk","family":"Hanzl\u00ed\u010dek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jind\u0159ich","family":"Matou\u0161ek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,6]]},"reference":[{"key":"26_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-030-00794-2_48","volume-title":"Text, Speech, and Dialogue","author":"Z Hanzl\u00ed\u010dek","year":"2018","unstructured":"Hanzl\u00ed\u010dek, Z., V\u00edt, J., Tihelka, D.: Wavenet-based speech synthesis applied to Czech. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 445\u2013452. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00794-2_48"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Henter, G.E., Merritt, T., Shannon, M., Mayo, C., King, S.: Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech. In: Proceedings of Interspeech, pp. 1504\u20131508 (2014)","DOI":"10.21437\/Interspeech.2014-361"},{"key":"26_CR3","unstructured":"Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of ICASSP 1996, pp. 373\u2013376 (1996)"},{"key":"26_CR4","unstructured":"International Telecommunications Union: Method for the subjective assessment of intermediate quality level of coding systems. ITU Recommendation ITU-R BS.1534-2 (2014)"},{"key":"26_CR5","unstructured":"J\u016fzov\u00e1, M., Tihelka, D., Matou\u0161ek, J., Hanzl\u00ed\u010dek, Z.: Voice conservation and TTS system for people facing total laryngectomy. In: Proceedings Interspeech 2017, pp. 3425\u20133426 (2017)"},{"key":"26_CR6","first-page":"2410","volume":"80","author":"N Kalchbrenner","year":"2018","unstructured":"Kalchbrenner, N., et al.: Efficient neural audio synthesis. Proc. Mach. Learn. Res. 80, 2410\u20132419 (2018)","journal-title":"Proc. Mach. Learn. Res."},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Morise, M., Toda, T., Banno, H., Nisimura, R., Irino, T.: Excitation source analysis for high-quality speech manipulation systems based on an interference-free representation of group delay with minimum phase response compensation. In: Proceedings of Interspeech, pp. 2243\u20132247 (2014)","DOI":"10.21437\/Interspeech.2014-247"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Lorenzo-Trueba, J., Drugman, T., Latorre, J., Merritt, T., Putrycz, B., Barra-Chicote, R.: Robust universal neural vocoding. CoRR abs\/1811.06292, submitted to ICASSP 2019 (2018)","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Tihelka, D., Psutka, J.: Automatic segmentation for Czech concatenative speech synthesis using statistical approach with boundary-specific correction. In: Proceedings of Eurospeech, pp. 301\u2013304 (2003)","DOI":"10.21437\/Eurospeech.2003-124"},{"key":"26_CR10","unstructured":"Matou\u0161ek, J., Tihelka, D., Romportl, J.: Building of a speech corpus optimised for unit selection TTS synthesis. In: Proceedings of LREC (2008)"},{"key":"26_CR11","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.specom.2016.09.001","volume":"84","author":"M Morise","year":"2016","unstructured":"Morise, M.: D4C, a band-aperiodicity estimator for high-quality speech synthesis. Speech Commun. 84, 57\u201365 (2016)","journal-title":"Speech Commun."},{"key":"26_CR12","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. CoRR abs\/1609.03499 (2016). http:\/\/arxiv.org\/abs\/1609.03499"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., Toda, T.: Speaker-dependent WaveNet vocoder. In: Proceedings of Interspeech, pp. 1118\u20131122 (2017)","DOI":"10.21437\/Interspeech.2017-314"},{"key":"26_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-00794-2_40","volume-title":"Text, Speech, and Dialogue","author":"D Tihelka","year":"2018","unstructured":"Tihelka, D., Hanzl\u00ed\u010dek, Z., J\u016fzov\u00e1, M., V\u00edt, J., Matou\u0161ek, J., Gr\u016fber, M.: Current state of text-to-speech system ARTIC: a decade of research on the field of speech technologies. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 369\u2013378. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00794-2_40"},{"key":"26_CR15","unstructured":"Zen, H.: Acoustic modeling in statistical parametric speech synthesis - from HMM to LSTM-RNN. In: Proceedings of MLSLP (2015)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27947-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:42:29Z","timestamp":1710348149000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27947-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030279462","9783030279479"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27947-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"6 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","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":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"inhouse TSD Web App 3.1","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - 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 (provided by the conference organizers)"}},{"value":"2-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,42","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1 full invited talk","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}