{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T19:30:46Z","timestamp":1771961446368,"version":"3.50.1"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319995786","type":"print"},{"value":"9783319995793","type":"electronic"}],"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_29","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"274-280","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Phoneme Duration Prediction for Kazakh Language"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8399-8379","authenticated-orcid":false,"given":"Arman","family":"Kaliyev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9095-3168","authenticated-orcid":false,"given":"Sergey V.","family":"Rybin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7010-1585","authenticated-orcid":false,"given":"Yuri N.","family":"Matveev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Arman K., Rybin, S.V., Matveev, Y.N., Kaziyeva, N., Burambayeva, N.,: Modeling pause for the synthesis of Kazakh speech. In: Proceedings of the Fourth International Conference on Engineering & MIS 2018 (ICEMIS 2018), Article 1, 4 p. ACM, New York, NY, USA, (2018). https:\/\/doi.org\/10.1145\/3234698.3234699","DOI":"10.1145\/3234698.3234699"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chen, B., Bian, T., Yu, K.: Discrete duration model for speech synthesis. In: 18th Annual Conference of the International Speech Communication Association, Interspeech 2017, Stockholm, Sweden, 20\u201324 August 2017, pp. 789\u2013793 (2017)","DOI":"10.21437\/Interspeech.2017-1144"},{"key":"29_CR3","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: 15th Annual Conference of the International Speech Communication Association, INTERSPEECH 2014, Singapore, 14\u201318 September 2014, pp. 2268\u20132272 (2014)","DOI":"10.21437\/Interspeech.2014-445"},{"issue":"2","key":"29_CR4","doi-asserted-by":"publisher","first-page":"197","DOI":"10.3758\/BF03204765","volume":"28","author":"PW Foltz","year":"1996","unstructured":"Foltz, P.W.: Latent semantic analysis for text-based research. Behav. Res. Methods Instrum. Comput. 28(2), 197\u2013202 (1996). https:\/\/doi.org\/10.3758\/BF03204765","journal-title":"Behav. Res. Methods Instrum. Comput."},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Henter, G.E., Ronanki, S., Watts, O., Wester, M., Wu, Z., King, S.: Robust TTS duration modelling using DNNs. In: Proceedings of the ICASSP, vol. 41. IEEE, Shanghai, March 2016. http:\/\/homepages.inf.ed.ac.uk\/ghenter\/pubs\/henter2016robust.pdf","DOI":"10.1109\/ICASSP.2016.7472655"},{"issue":"8","key":"29_CR6","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). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"29_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1007\/978-3-319-66429-3_74","volume-title":"Speech and Computer","author":"A Kaliyev","year":"2017","unstructured":"Kaliyev, A., Rybin, S.V., Matveev, Y.: The pausing method based on brown clustering and word embedding. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 741\u2013747. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_74"},{"key":"29_CR8","unstructured":"Karpov, A., Verkhodanova, V.: Speech technologies for under-resourced languages of the world 2015, pp. 117\u2013135 (2015)"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-319-23132-7_3","volume-title":"Speech and Computer","author":"O Khomitsevich","year":"2015","unstructured":"Khomitsevich, O., Mendelev, V., Tomashenko, N., Rybin, S., Medennikov, I., Kudubayeva, S.: A bilingual Kazakh-Russian system for automatic speech recognition and synthesis. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS (LNAI), vol. 9319, pp. 25\u201333. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23132-7_3"},{"key":"29_CR10","unstructured":"Koo, T., Carreras, X., Collins, M.: Simple semi-supervised dependency parsing. In: Proceedings of ACL 2008: HLT, pp. 595\u2013603. Association for Computational Linguistics, Columbus, June 2008. http:\/\/www.aclweb.org\/anthology\/P\/P08\/P08-1068"},{"key":"29_CR11","unstructured":"Miller, S., Guinness, J., Zamanian, A.: Name tagging with word clusters and discriminative training. In: Susan Dumais, D.M., Roukos, S. (eds.) HLT-NAACL 2004: Main Proceedings, pp. 337\u2013342. Association for Computational Linguistics, Boston, 2\u20137 May 2004. http:\/\/www.aclweb.org\/anthology\/N04-1043"},{"key":"29_CR12","unstructured":"Ronanki, S., Watts, O., King, S., Henter, G.E.: Median-based generation of synthetic speech durations using a non-parametric approach. CoRR abs\/1608.06134 (2016). http:\/\/arxiv.org\/abs\/1608.06134"},{"key":"29_CR13","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":"29_CR14","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A.W.: Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, 4\u20139 May 2014, pp. 3844\u20133848 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6854321","DOI":"10.1109\/ICASSP.2014.6854321"}],"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_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T04:57:18Z","timestamp":1661835438000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}