{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:36:18Z","timestamp":1763620578738,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030279462"},{"type":"electronic","value":"9783030279479"}],"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_31","type":"book-chapter","created":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T23:02:43Z","timestamp":1567378963000},"page":"361-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["LSTM-Based Speech Segmentation for TTS Synthesis"],"prefix":"10.1007","author":[{"given":"Zden\u011bk","family":"Hanzl\u00ed\u010dek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakub","family":"V\u00edt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Tihelka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,6]]},"reference":[{"key":"31_CR1","unstructured":"Adell, J., Bonafonte, A., G\u00f3mez, J.A., Bleda, M.J.C.: Comparative study of automatic phone segmentation methods for TTS. In: Proceedings of ICASSP, pp. 309\u2013312 (2005)"},{"issue":"1","key":"31_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/TASLP.2015.2456421","volume":"24","author":"S Brognaux","year":"2016","unstructured":"Brognaux, S., Drugman, T.: HMM-based speech segmentation: Improvements of fully automatic approaches. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(1), 5\u201315 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"31_CR3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/0167-6393(93)90083-W","volume":"12","author":"F Brugnara","year":"1993","unstructured":"Brugnara, F., Falavigna, D., Omologo, M.: Automatic segmentation and labeling of speech based on hidden Markov models. Speech Commun. 12, 357\u2013370 (1993)","journal-title":"Speech Commun."},{"key":"31_CR4","unstructured":"Finster, H.: Automatic speech segmentation using neural network and phonetic transcription. In: Proceedings of IJCNN (1992)"},{"key":"31_CR5","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2","volume-title":"Supervised Sequence Labelling with Recurrent Neural Networks","author":"A Graves","year":"2012","unstructured":"Graves, A.: Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence, vol. 385. Springer, Heidelberg (2012)"},{"key":"31_CR6","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: Proceedings of ICML, pp. 1764\u20131772 (2014)"},{"key":"31_CR7","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18, 602\u2013610 (2005)","journal-title":"Neural Netw."},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Haubold, A., Kender, J.R.: Alignment of speech to highly imperfect text transcriptions. In: Proceedings of ICME, pp. 224\u2013227 (2007)","DOI":"10.1109\/ICME.2007.4284627"},{"key":"31_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Hoffmann, S., Pfister, B.: Fully automatic segmentation for prosodic speech corpora. In: Proceedings of Interspeech, pp. 1389\u20131392 (2010)","DOI":"10.21437\/Interspeech.2010-423"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Hoffmann, S., Pfister, B.: Text-to-speech alignment of long recordings using universal phone models. In: Proceedings of Interspeech, pp. 1520\u20131524 (2013)","DOI":"10.21437\/Interspeech.2013-307"},{"key":"31_CR12","unstructured":"Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of ICASSP, pp. 373\u2013376 (1996)"},{"key":"31_CR13","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 of Interspeech, Stockholm, Sweden, pp. 3425\u20133426 (2017)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Kominek, J., Bennett, C.L., Black, A.W.: Evaluating and correcting phoneme segmentation for unit selection synthesis. In: Proceedings of Eurospeech, pp. 313\u2013316 (2003)","DOI":"10.21437\/Eurospeech.2003-127"},{"issue":"4","key":"31_CR15","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/S0167-6393(02)00131-0","volume":"40","author":"F. Malfr\u00e8re","year":"2003","unstructured":"Malfr\u00e8re, F., Deroo, O., Dutoit, T., Risa, C.: Phonetic alignment: speech synthesis-based vs. viterbi-based. Speech Commun. 40, 503\u2013515 (2003)","journal-title":"Speech Communication"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Romportl, J.: Automatic pitch-synchronous phonetic segmentation. In: Proceedings of Interspeech, pp. 1626\u20131629 (2008)","DOI":"10.21437\/Interspeech.2008-452"},{"key":"31_CR17","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":"31_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-3-540-39398-6_41","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2003","unstructured":"Matou\u0161ek, J., Tihelka, D., Psutka, J.: Experiments with automatic segmentation for czech speech synthesis. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2003. LNCS (LNAI), vol. 2807, pp. 287\u2013294. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-39398-6_41"},{"key":"31_CR19","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":"31_CR20","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\u00a0decade 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":"31_CR21","unstructured":"Toledano, D.T.: Neural network boundary refining for automatic speech segmentation. In: Proceedings of ICASSP, pp. 3438\u20133441 (2000)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Improved DNN-based segmentation for multi-genre broadcast audio. In: Proceedings of ICASSP, pp. 5700\u20135704 (2016)","DOI":"10.1109\/ICASSP.2016.7472769"},{"key":"31_CR23","unstructured":"Wells, J.: SAMPA computer readable phonetic alphabet. In: Handbook of Standards and Resources for Spoken Language Systems, pp. 684\u2013732. Mouton de Gruyter, Berlin (1997)"}],"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_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:43:30Z","timestamp":1710348210000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27947-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030279462","9783030279479"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27947-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}