{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T02:40:17Z","timestamp":1717900817186},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,5,19]],"date-time":"2015-05-19T00:00:00Z","timestamp":1431993600000},"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":["J Sign Process Syst"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s11265-015-1011-7","type":"journal-article","created":{"date-parts":[[2015,5,18]],"date-time":"2015-05-18T02:55:25Z","timestamp":1431917725000},"page":"273-286","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Superpositional HMM-Based Intonation Synthesis Using a Functional F0 Model"],"prefix":"10.1007","volume":"82","author":[{"given":"Jinfu","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiori","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,19]]},"reference":[{"key":"1011_CR1","doi-asserted-by":"crossref","first-page":"271","DOI":"10.7551\/mitpress\/3839.003.0016","volume-title":"Intentions in communication","author":"J Pierrehumbert","year":"1990","unstructured":"Pierrehumbert, J., & Hirschberg, J. (1990). The meaning of intonational contours in the interpretation of discourse In Cohen, P., Morgan, J., & P.llack, M. (Eds.), Intentions in communication, (pp. 271\u2013311). Cambridge: MIT Press."},{"key":"1011_CR2","doi-asserted-by":"crossref","unstructured":"Taylor, P. (2009). Text-to-speech synthesis: Cambridge University Press.","DOI":"10.1017\/CBO9780511816338"},{"issue":"11","key":"1011_CR3","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen, H., Tokuda, K., & Black, A. (2009). Statistical parametric speech synthesis. Speech Communication, 51(11), 1039\u2013 1064.","journal-title":"Speech Communication"},{"issue":"5","key":"1011_CR4","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1093\/ietisy\/e90-d.5.825","volume":"E90-D","author":"H Zen","year":"2007","unstructured":"Zen, H., Tokuda, K., Nasuko, T., Kobayashi, T., & Kitamura, T. (2007). A hidden semi-Markov model-based speech synthesis system. IEICE Transactions on Information Systems, E90-D(5), 825\u2013834.","journal-title":"IEICE Transactions on Information Systems"},{"issue":"5","key":"1011_CR5","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1093\/ietisy\/e90-d.5.816","volume":"E90-D","author":"T Toda","year":"2007","unstructured":"Toda, T., & Tokuda, K. (2007). A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Transactions on Information Systems, E90-D(5), 816\u2013824.","journal-title":"IEICE Transactions on Information Systems"},{"key":"1011_CR6","unstructured":"Hunt, A, & Black, A. (1996). Unit selection in a cancatenative speech synthesis system using a large speech database. In ICASSP1996 (pp. 373\u2013376)."},{"issue":"5","key":"1011_CR7","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TASL.2010.2045237","volume":"18","author":"J Yamagishi","year":"2010","unstructured":"Yamagishi, J., Usabaev, B., King, S., Watts, O., Dines, J., Tian, J., Guan, Y., Hu, R., Oura, K., Wu, Y.J., Tokuda, K., Karhila, R., & Kurimo, M. (2010). Thousands of voices for HMM-based speech synthesis \u2014 analysis and application of TTS systems built on various ASR corpora. IEEE Transactions on Audio, Speech, and Language Processing, 18(5), 984\u20131004.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"1011_CR8","doi-asserted-by":"crossref","unstructured":"Ni, J., & Kawai, H. (2010). An unsupervised approach to creating web audio contents-based HMM voices. In Proceedings of INTERSPEECH2010 (pp. 849\u2013852).","DOI":"10.21437\/Interspeech.2010-189"},{"key":"1011_CR9","unstructured":"Maeno, Y., Nose, T., Kobayashi, T., Ijima, Y., Nakajima, H., Mizuno, H., & Yoshioka, O. (2011). HMM-based emphatic speech synthesis using unsupervised context labelling. In Proceedings of INTERSPEECH2011 (pp. 1849\u20131852)."},{"key":"1011_CR10","unstructured":"Kawai, H., Toda, T., Ni, J., Tsuzaki, M., & Tokuda, K. (2004). XIMERA: a new TTS from ATR based on corpus-based technologies. In 5th ISCA Speech Synthesis Workshop (pp. 179\u2013184)."},{"key":"1011_CR11","unstructured":"Tokuda, K., Masuko, T., Miyazaki, N., & Kobayashi, T. (1999). Hidden Markov models based on multispace probability distribution for pitch pattern modeling. In proceedings of ICASSP1999 (pp. 229\u2013232)."},{"key":"1011_CR12","doi-asserted-by":"crossref","unstructured":"Santen, J., & Hirschberg, J. (1994). Segmental effect on timing and height of pitch contours. In in Proceedings of ICSLP1994.","DOI":"10.21437\/ICSLP.1994-182"},{"issue":"5","key":"1011_CR13","first-page":"1071","volume":"19","author":"K Yu","year":"2011","unstructured":"Yu, K., & Young, S. (2011). Continuous F0 modelling for HMM based statistical parametric speech synthesis. IEEE Transactions on ASLP, 19(5), 1071\u20131079.","journal-title":"IEEE Transactions on ASLP"},{"issue":"3","key":"1011_CR14","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1093\/ietisy\/e88-d.3.489","volume":"E88D","author":"S Sakai","year":"2005","unstructured":"Sakai, S. (2005). Fundamental frequency modeling for speech synthesis based on a statistical learning technique. IEICE Transactions on Information Systems, E88D(3), 489\u2013495.","journal-title":"IEICE Transactions on Information Systems"},{"key":"1011_CR15","doi-asserted-by":"crossref","unstructured":"Wu, Y.J., & Soong, F. (2012). Modeling pitch trajectory by hierarchical HMM with minimum generation error training. In Proceedings of ICASSP2012 (pp. 4017\u20134020).","DOI":"10.1109\/ICASSP.2012.6288799"},{"key":"1011_CR16","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1017\/S095267570000066X","volume":"3","author":"ME Beckman","year":"1986","unstructured":"Beckman, M.E., & Pierrehumbert, J.B. (1986). Intonational structure in Japanese and English. Phonology Yearbook, 3, 255\u2013309.","journal-title":"Phonology Yearbook"},{"key":"1011_CR17","doi-asserted-by":"crossref","unstructured":"\u2019tHart, J., Collier, R., & Cohen, A. (1990). A perceptual study of intonation: an experimental-phonetic approach to speech melody: Cambridge University Press.","DOI":"10.1017\/CBO9780511627743"},{"key":"1011_CR18","doi-asserted-by":"crossref","unstructured":"Fujisaki, H. (2004). Information, prosody, and modeling \u2014 with emphasis on tonal features of speech \u2014. In proceedings of Speech Prosody 2004 (pp. 1\u201310).","DOI":"10.21437\/SpeechProsody.2004-1"},{"key":"1011_CR19","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1250\/ast.5.233","volume":"5","author":"H Fujisaki","year":"1984","unstructured":"Fujisaki, H., & Hirose, K. (1984). Analysis of voice fundamental frequency contours for declarative sentences of Japanese. Journal of the Acoustical Society of Japan, 5, 233\u2013242.","journal-title":"Journal of the Acoustical Society of Japan"},{"key":"1011_CR20","first-page":"25","volume":"40","author":"E Garding","year":"1993","unstructured":"Garding, E. (1993). On parameters and principles in intonation analysis, Lund University, Department of Linguistics. Working Papers, 40, 25\u201347.","journal-title":"Working Papers"},{"key":"1011_CR21","unstructured":"van Santen, J., Mashira, T., & Klabbers, E. (2004). Estimating phrase curves in the general superpositional intonation model. In Proceedings of the 5th Speech Synthesis Workshop (pp. 61\u201366)."},{"issue":"4","key":"1011_CR22","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1250\/ast.33.221","volume":"33","author":"T Matsuda","year":"2012","unstructured":"Matsuda, T., Hirose, K., & Minematsu, N. (2012). Applying generation process model constraint to fundamental frequency contours generated by hidden-Markove-model-based speech synthesis. Acoustical Science and Technology, 33(4), 221\u2013228.","journal-title":"Acoustical Science and Technology"},{"key":"1011_CR23","doi-asserted-by":"crossref","unstructured":"Hashimoto, H., Hirose, K., & Minematsu, N. (2012). Improved automatic extraction of generation process model commands and its use for generating fundamental frequency contours for training HMM-based speech synthesis. In Proceedings of INTERSPEECH2012.","DOI":"10.21437\/Interspeech.2012-157"},{"key":"1011_CR24","doi-asserted-by":"crossref","unstructured":"Sakurai, A., & Hirose, K. (1996). Detection of phrase boundaries in Japanese by low-pass filtering of fundamental frequency contours. In Proceedings of ICSLP1996 (pp. 817\u2013820).","DOI":"10.1109\/ICSLP.1996.607726"},{"key":"1011_CR25","doi-asserted-by":"crossref","unstructured":"Mixdorff, H. (2000). A novel approach to the fully automatic extraction of fujisaki model parameters. In Proceedings of ICASSP 2000, (Vol. 3 pp. 1281\u20131284).","DOI":"10.1109\/ICASSP.2000.861811"},{"key":"1011_CR26","doi-asserted-by":"crossref","unstructured":"Narusawa, S., Minematsu, N., Hirose, K., & Fujisaki, H. (2002). A method for automatic extraction of model parameters from fundamental frequency contours of speech. In proceedings of ICASSP 2002, pp. I-509 \u2013 I-512.","DOI":"10.1109\/ICASSP.2002.5743766"},{"key":"1011_CR27","doi-asserted-by":"crossref","unstructured":"Langarani, M., Klabbers, E., & Santen, J. (2014). A novel pitch decomposition method for the generalized linear alignment model. In Proceedings of ICASSP2014 (pp. 2603\u20132607).","DOI":"10.1109\/ICASSP.2014.6854067"},{"key":"1011_CR28","doi-asserted-by":"crossref","unstructured":"Kameoka, H., Yoshizato, K., Ishihara, T., Ohishi, Y., Kashino, K., & Sagayama, S. (2013). Generative modeling of speech F0 contours. In Proceedings of INTERSPEECH2013 (pp. 1826\u20131830).","DOI":"10.21437\/Interspeech.2013-450"},{"key":"1011_CR29","doi-asserted-by":"crossref","unstructured":"Ni, J., Shiga, Y., Hori, C., & Kidawara, Y. (2013). A targets-based superpositional model of fundamental frequency contours applied to HMM-based speech synthesis. In Proceedings of INTERSPEECH2013 (pp. 1052\u20131056).","DOI":"10.21437\/Interspeech.2013-117"},{"key":"1011_CR30","unstructured":"Mishira, T. (2008). Decomposition of fundamental frequency contours in the general superpositional intonation model, PhD. thesis, the Oregon Health & Science University."},{"key":"1011_CR31","doi-asserted-by":"crossref","unstructured":"Ni, J., & Nakamura, S. (2007). Use of Poisson processes to generate fundamental frequency contours. In Proceedings of ICASSP2007 (pp. 825\u2013828).","DOI":"10.1109\/ICASSP.2007.367040"},{"issue":"3","key":"1011_CR32","doi-asserted-by":"crossref","first-page":"1764","DOI":"10.1121\/1.2165071","volume":"119","author":"J Ni","year":"2006","unstructured":"Ni, J., Kawai, H., & Hirose, K. (2006). Constrained tone transformation technique for separation and combination of Mandarin tone and intonation. Journal of the Acoustical Society of America, 119(3), 1764\u20131782.","journal-title":"Journal of the Acoustical Society of America"},{"key":"1011_CR33","doi-asserted-by":"crossref","unstructured":"Venditti, J., Maekawa, K., & Beckman, M. (2008). Prominence marking in the Japanese intonation system, The Oxford Handbook of Japanese Linguistics: Oxford University Press.","DOI":"10.1093\/oxfordhb\/9780195307344.013.0017"},{"key":"1011_CR34","unstructured":"http:\/\/hts.sp.nitech.ac.jp\/ ."},{"key":"1011_CR35","doi-asserted-by":"crossref","unstructured":"Clark, R., & Dusterhoff, K. (1999). Objective methods for evaluating synthetic intonation. In Proceedings of Eurospeech 1999, (Vol. 4 pp. 1623\u20131626).","DOI":"10.21437\/Eurospeech.1999-368"},{"issue":"3","key":"1011_CR36","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1587\/transinf.E93.D.595","volume":"E93-D","author":"K Oura","year":"2010","unstructured":"Oura, K., Zen, H., Nankaku, Y., Lee, A., & Tokuda, K. (2010). A covariance-tying technique for HMM-based speech synthesis. IEICE Transactions on Information Systems, E93-D(3), 595\u2013601.","journal-title":"IEICE Transactions on Information Systems"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1011-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-1011-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1011-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T01:51:43Z","timestamp":1717897903000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-1011-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,19]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1011"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-1011-7","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5,19]]}}}