{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:53Z","timestamp":1740099113262,"version":"3.37.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"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\/978-3-319-99579-3_27","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"255-263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["On the Comparison of Different Phrase Boundary Detection Approaches Trained on Czech TTS Speech Corpora"],"prefix":"10.1007","author":[{"given":"Mark\u00e9ta","family":"J\u016fzov\u00e1","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"27_CR1","first-page":"2493","volume":"999888","author":"R Collobert","year":"2011","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 999888, 2493\u20132537 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Fernandez, R., Rendel, A., Ramabhadran, B., Hoory, R.: Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks. In: Proceedings of Interspeech 2014, pp. 2268\u20132272. ISCA, September 2014","DOI":"10.21437\/Interspeech.2014-445"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Gregory, M.L.: Using conditional random fields to predict pitch accents in conversational speech. In: Proceedings of ACL 2004. ACL, East Stroudsburg, pp. 677\u2013684 (2004)","DOI":"10.3115\/1218955.1219041"},{"key":"27_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-319-45510-5_47","volume-title":"Text, Speech, and Dialogue","author":"Z Hanzl\u00ed\u010dek","year":"2016","unstructured":"Hanzl\u00ed\u010dek, Z.: Correction of prosodic phrases in large speech corpora. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2016. LNCS (LNAI), vol. 9924, pp. 408\u2013417. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-45510-5_47"},{"issue":"3","key":"27_CR5","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/0167-6393(96)00017-9","volume":"18","author":"J Hirschberg","year":"1996","unstructured":"Hirschberg, J., Prieto, P.: Training intonational phrasing rules automatically for English and Spanish text-to-speech. Speech Commun. 18(3), 281\u2013290 (1996)","journal-title":"Speech Commun."},{"key":"27_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-319-66429-3_26","volume-title":"Speech and Computer","author":"M J\u016fzov\u00e1","year":"2017","unstructured":"J\u016fzov\u00e1, M.: CRF-based phrase boundary detection trained on large-scale TTS speech corpora. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 272\u2013281. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_26"},{"key":"27_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/978-3-319-64206-2_19","volume-title":"Text, Speech, and Dialogue","author":"M J\u016fzov\u00e1","year":"2017","unstructured":"J\u016fzov\u00e1, M.: Prosodic phrase boundary classification based on Czech speech corpora. In: Ek\u0161tein, K., Matou\u0161ek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 165\u2013173. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64206-2_19"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"J\u016fzov\u00e1, M., Tihelka, D., Vol\u00edn, J.: On the extension of the formal prosody model for TTS. In: Text, Speech and Dialogue. Lecture Notes in Computer Science, Springer, Heidelberg (2018)","DOI":"10.1007\/978-3-030-00794-2_38"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Koehn, P., Abney, S., Hirschberg, J., Collins, M.: Improving intonational phrasing with syntactic information. In: Proceedings of 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 1289\u20131290 (2000)","DOI":"10.1109\/ICASSP.2000.861813"},{"key":"27_CR10","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning, pp. 282\u2013289. Morgan Kaufmann Publishers Inc., San Francisco (2001)"},{"key":"27_CR11","first-page":"1641","volume":"2007","author":"M Leg\u00e1t","year":"2007","unstructured":"Leg\u00e1t, M., Matou\u0161ek, J., Tihelka, D.: A robust multi-phase pitch-mark detection algorithm. Proc. Interspeech 2007, 1641\u20131644 (2007)","journal-title":"Proc. Interspeech"},{"issue":"4","key":"27_CR12","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1016\/j.specom.2011.01.008","volume":"53","author":"M Leg\u00e1t","year":"2011","unstructured":"Leg\u00e1t, M., Matou\u0161ek, J., Tihelka, D.: On the detection of pitch marks using a robust multi-phase algorithm. Speech Commun. 53(4), 552\u2013566 (2011)","journal-title":"Speech Commun."},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Louw, A., Moodley, A.: Speaker specific phrase break modeling with conditional random fields for text-to-speech. In: Proceedings of 2016 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), pp. 1\u20136 (2016)","DOI":"10.1109\/RoboMech.2016.7813163"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Romportl, J.: Automatic pitch-synchronous phonetic segmentation. In: Proceedings of Interspeech 2008, pp. 1626\u20131629. ISCA (2008)","DOI":"10.21437\/Interspeech.2008-452"},{"key":"27_CR15","unstructured":"Matou\u0161ek, J., Leg\u00e1t, M.: Is unit selection aware of audible artifacts? SSW 2013. In: Proceedings of the 8th Speech Synthesis Workshop, pp. 267\u2013271. ISCA, Barcelona (2013)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Tihelka, D.: Classification-based detection of glottal closure instants from speech signals. In: Proceedings of Interspeech 2017, pp. 3053\u20133057. ISCA (2017)","DOI":"10.21437\/Interspeech.2017-213"},{"key":"27_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/11846406_55","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2006","unstructured":"Matou\u0161ek, J., Tihelka, D., Romportl, J.: Current state of Czech text-to-speech system ARTIC. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2006. LNCS (LNAI), vol. 4188, pp. 439\u2013446. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11846406_55"},{"key":"27_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/978-3-540-74628-7_43","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2007","unstructured":"Matou\u0161ek, J., Romportl, J.: Recording and annotation of speech corpus for Czech unit selection speech synthesis. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2007. LNCS (LNAI), vol. 4629, pp. 326\u2013333. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74628-7_43"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Tihelka, D.: Annotation errors detection in TTS corpora. In: Proceedings of Interspeech 2013, pp. 1511\u20131515. ISCA (2013)","DOI":"10.21437\/Interspeech.2013-305"},{"key":"27_CR20","unstructured":"Mikolov, T., Yih, W.T., Zweig, G.: Linguistic regularities in continuous space word representations. In: Proceedings of 2013 NAACL HLT, pp. 746\u2013751 (2013)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Mishra, T., Jun Kim, Y., Bangalore, S.: Intonational phrase break prediction for text-to-speech synthesis using dependency relations. In: Proceedings of ICASSP 2015, pp. 4919\u20134923 (2015)","DOI":"10.1109\/ICASSP.2015.7178906"},{"key":"27_CR22","unstructured":"Palkov\u00e1, Z.: Rytmick\u00e1 v\u00fdstavba prozaick\u00e9ho textu. Studia \u010cSAV; \u010dis. 13\/1974, Academia (1974)"},{"key":"27_CR23","first-page":"4013","volume":"2012","author":"A Parlikar","year":"2012","unstructured":"Parlikar, A., Black, A.W.: Data-driven phrasing for speech synthesis in low-resource languages. Proc. ICASSP 2012, 4013\u20134016 (2012)","journal-title":"Proc. ICASSP"},{"key":"27_CR24","unstructured":"Prahallad, K., Raghavendra, E.V., Black, A.W.: Learning speaker-specific phrase breaks for text-to-speech systems. In: The 7th ISCA Tutorial and Research Workshop on Speech Synthesis, pp. 162\u2013166 (2010)"},{"issue":"3","key":"27_CR25","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1016\/j.csl.2006.09.004","volume":"21","author":"I Read","year":"2007","unstructured":"Read, I., Cox, S.: Stochastic and syntactic techniques for predicting phrase breaks. Comput. Speech Lang. 21(3), 519\u2013542 (2007)","journal-title":"Comput. Speech Lang."},{"key":"27_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/11551874_48","volume-title":"Text, Speech and Dialogue","author":"J Romportl","year":"2005","unstructured":"Romportl, J., Matou\u0161ek, J.: Formal prosodic structures and their application in NLP. In: Matou\u0161ek, V., Mautner, P., Pavelka, T. (eds.) TSD 2005. LNCS (LNAI), vol. 3658, pp. 371\u2013378. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11551874_48"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Romportl, J.: Structural data-driven prosody model for TTS synthesis. In: Proceedings of Speech Prosody 2006, pp. 549\u2013552. TUDpress, Dresden (2006)","DOI":"10.21437\/SpeechProsody.2006-121"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Romportl, J.: Automatic prosodic phrase annotation in a corpus for speech synthesis. In: Proceedings of Speech Prosody 2010. University of Illionois, Chicago (2010)","DOI":"10.21437\/SpeechProsody.2010-129"},{"key":"27_CR29","doi-asserted-by":"publisher","first-page":"51","DOI":"10.2478\/v10108-011-0004-3","volume":"95","author":"J Romportl","year":"2011","unstructured":"Romportl, J., Matou\u0161ek, J.: Several aspects of machine-driven phrasing in text-to-speech systems. Prague Bull. Math. Linguist. 95, 51\u201361 (2011)","journal-title":"Prague Bull. Math. Linguist."},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Rosenberg, A., Fernandez, R., Ramabhadran, B.: Modeling phrasing and prominence using deep recurrent learning. In: Proceedings of Interspeech 2015, pp. 3066\u20133070. ISCA (2015)","DOI":"10.21437\/Interspeech.2015-623"},{"key":"27_CR31","first-page":"3","volume":"2001","author":"X Sun","year":"2001","unstructured":"Sun, X., Applebaum, T.H.: Intonational phrase break prediction using decision tree and n-gram model. Proc. Eurospeech 2001, 3\u20137 (2001)","journal-title":"Proc. Eurospeech"},{"key":"27_CR32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338","volume-title":"Text-to-Speech Synthesis","author":"P Taylor","year":"2009","unstructured":"Taylor, P.: Text-to-Speech Synthesis, 1st edn. Cambridge University Press, New York (2009)","edition":"1"},{"issue":"2","key":"27_CR33","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1006\/csla.1998.0041","volume":"12","author":"P Taylor","year":"1998","unstructured":"Taylor, P., Black, A.W.: Assigning phrase breaks from part-of-speech sequences. Comput. Speech Lang. 12(2), 99\u2013117 (1998)","journal-title":"Comput. Speech Lang."},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Tihelka, D.: Symbolic prosody driven unit selection for highly natural synthetic speech. In: Proceedings of Interspeech 2005 - Eurospeech, pp. 2525\u20132528. ISCA (2005)","DOI":"10.21437\/Interspeech.2005-786"},{"key":"27_CR35","doi-asserted-by":"crossref","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: Text, Speech and Dialogue. Lecture Notes in Computer Science, Springer, Heidelberg (2018)","DOI":"10.1007\/978-3-030-00794-2_40"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Tihelka, D., Kala, J., Matou\u0161ek, J.: Enhancements of Viterbi search for fast unit selection synthesis. In: Proceedings of Interspeech 2010, pp. 174\u2013177. ISCA (2010)","DOI":"10.21437\/Interspeech.2010-78"},{"key":"27_CR37","unstructured":"Turian, J., Ratinov, L., Bengio, Y.: Word representations: a simple and general method for semisupervised learning. In: Proceedings of ACL 2010, pp. 384\u2013394. ACL (2010)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T15:22:49Z","timestamp":1720538569000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}