{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:10:38Z","timestamp":1742991038698,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319491684"},{"type":"electronic","value":"9783319491691"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-49169-1_7","type":"book-chapter","created":{"date-parts":[[2016,11,3]],"date-time":"2016-11-03T11:31:46Z","timestamp":1478172706000},"page":"64-72","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Prosodic Break Prediction with RNNs"],"prefix":"10.1007","author":[{"given":"Santiago","family":"Pascual","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio","family":"Bonafonte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,4]]},"reference":[{"key":"7_CR1","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. Cambridge University Press, Cambridge (2009)"},{"key":"7_CR2","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, 99\u2013117 (1998)","journal-title":"Comput. Speech Lang."},{"key":"7_CR3","unstructured":"Bonafonte, A., Ag\u00fcero, P.D.: Phrase break prediction using a finite state transducer. In: Proceedings of Advanced Speech Technologies (2004)"},{"key":"7_CR4","unstructured":"Ag\u00fcero, P.D., et al.: S\u00edntesis de voz aplicada a la traducci\u00f3n voz a voz. Ph.D. dissertation, Tesis Doctoral. Universidad Polit\u00e9cnica de Catalu\u00f1a (2012). http:\/\/hdl.handle.net\/10803\/97035"},{"issue":"3","key":"7_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":"7_CR6","first-page":"56","volume":"18","author":"J Li","year":"2004","unstructured":"Li, J., Hu, G., Wang, R.: Prosody phrase break prediction based on maximum entropy model. J. Chin. Inf. Process. 18, 56\u201363 (2004)","journal-title":"J. Chin. Inf. Process."},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Watts, O., Gangireddy, S., Yamagishi, J., King, S., Renals, S., Stan, A., Giurgiu, M.: Neural net word representations for phrase-break prediction without a part of speech tagger. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2599\u20132603. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854070"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Mishra, T., Kim, Y.-J., Bangalore, S.: Intonational phrase break prediction for text-to-speech synthesis using dependency relations. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4919\u20134923. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178906"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Watts, O., Yamagishi, J., King, S.: Unsupervised continuous-valued word features for phrase-break prediction without a part-of-speech tagger. In: INTERSPEECH, pp. 2157\u20132160 (2011)","DOI":"10.21437\/Interspeech.2011-565"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Sun, X., Applebaum, T.H.: Intonational phrase break prediction using decision tree and n-gram model. In: INTERSPEECH, pp. 537\u2013540 (2001)","DOI":"10.21437\/Eurospeech.2001-144"},{"issue":"3\u20134","key":"7_CR11","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng, L., Yu, D.: Deep learning: methods and applications. Found. Trends Sig. Process. 7(3\u20134), 197\u2013387 (2014)","journal-title":"Found. Trends Sig. Process."},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models, arXiv preprint arXiv:1508.06615 (2015)","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"7_CR13","unstructured":"Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1017\u20131024 (2011)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Deoras, A., Kombrink, S., Burget, L., Cernock\u1ef3, J.: Empirical evaluation and combination of advanced language modeling techniques. In: INTERSPEECH, pp. 605\u2013608 (2011)","DOI":"10.21437\/Interspeech.2011-242"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"7_CR16","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: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4470\u20134474 (2015)","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"7_CR17","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: INTERSPEECH, pp. 1964\u20131968 (2014)","DOI":"10.21437\/Interspeech.2014-443"},{"issue":"02","key":"7_CR18","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1142\/S0218488598000094","volume":"6","author":"S Hochreiter","year":"1998","unstructured":"Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertainty Fuzziness Knowl.-Based Syst. 6(02), 107\u2013116 (1998)","journal-title":"Int. J. Uncertainty Fuzziness Knowl.-Based Syst."},{"issue":"8","key":"7_CR19","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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR20","unstructured":"Chollet, F.: Keras (2015). https:\/\/github.com\/fchollet\/keras"},{"key":"7_CR21","unstructured":"Bonafonte, A., H\u00f6ge, H., Kiss, I., Moreno, A., Ziegenhain, U., van den Heuvel,\u00a0H., Hain, H.-U., Wang, X.S., Garcia, M.-N.: TC-STAR: specifications of language resources and evaluation for speech synthesis. In: Proceedings of LREC Conference, pp. 311\u2013314 (2006)"},{"key":"7_CR22","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 1139\u20131147 (2013)"},{"issue":"3","key":"7_CR23","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/PROC.1973.9030","volume":"61","author":"JD Forney Jr","year":"1973","unstructured":"Forney Jr., J.D.: The viterbi algorithm. Proc. IEEE 61(3), 268\u2013278 (1973)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Advances in Speech and Language Technologies for Iberian Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49169-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T10:30:29Z","timestamp":1710325829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-49169-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319491684","9783319491691"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49169-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IberSPEECH","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advances in Speech and Language Technologies for Iberian Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iberspeech2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iberspeech2016.inesc-id.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}