{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:35:53Z","timestamp":1778301353694,"version":"3.51.4"},"reference-count":27,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2003,6,1]],"date-time":"2003-06-01T00:00:00Z","timestamp":1054425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2003,6]]},"DOI":"10.1016\/s0167-6393(02)00177-2","type":"journal-article","created":{"date-parts":[[2003,5,13]],"date-time":"2003-05-13T04:46:45Z","timestamp":1052801205000},"page":"535-549","source":"Crossref","is-referenced-by-count":17,"title":["Data-driven generation of F0 contours using a superpositional model"],"prefix":"10.1016","volume":"40","author":[{"given":"A.","family":"Sakurai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K.","family":"Hirose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Minematsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(02)00177-2_BIB1","series-title":"Talking Machines: Theories, Models, and Designs","first-page":"307","article-title":"Developing a structured lexicon for synthesis of prosody","author":"Auberg\u00e9","year":"1992"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB2","series-title":"Classification and Regression Trees","author":"Brieman","year":"1984"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB3","first-page":"317","article-title":"J-ToBI: An intonation labelling system for Japanese","author":"Campbell","year":"1995","journal-title":"Fall Mtg. Acoust. Soc. Jpn"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB4","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/89.668817","article-title":"An RNN-based prosodic information synthesizer for Mandarin text-to-speech","volume":"6\u20133","author":"Chen","year":"1998","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(02)00177-2_BIB5","unstructured":"Fujisaki, H., 1999. The fundamental frequency contour of speech\u2013\u2013its modeling, underlying mechanisms, and application to multilingual speech synthesis. In: Proc. Int. Conf. Speech Process., Seoul. Vol. 1, pp. 19\u201326"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB6","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1250\/ast.5.233","article-title":"Analysis of voice fundamental frequency contours for declarative sentences of Japanese","volume":"5\u20134","author":"Fujisaki","year":"1984","journal-title":"J. Acoust. Soc. Jpn."},{"key":"10.1016\/S0167-6393(02)00177-2_BIB7","unstructured":"Fujisaki, H., Hirose, K., Takahashi, N., 1993. Manifestation of linguistic information in the voice fundamental frequency contours of spoken Japanese. IEICE Trans. Fundam. E-76-A, 11, 1919\u20131926"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB8","doi-asserted-by":"crossref","unstructured":"Fujisaki, H., Hirose, K., Takahashi N., Morikawa, H., 1986. Acoustic characteristics and the underlying rules of intonation of the common Japanese used by radio and television announcers. In: Proc. ICASSP\u20191986. pp. 2039\u20132042","DOI":"10.1109\/ICASSP.1986.1168659"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB9","unstructured":"Fujisaki, H., Ohno, S., Wang, C., 1998. A command\u2013response model for F0 contour generation in multilingual speech synthesis. In: Proc. of the 3rd ESCA\/COCOSDA Intern. Workshop on Speech Synthesis. pp. 299\u2013304"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB10","doi-asserted-by":"crossref","unstructured":"Fujisaki, H., Tomana, R., Narusawa, S., Ohno, S., Wang, C., 2000. Physiological mechanisms for fundamental frequency control in standard Chinese. Proc. ICSLP\u20192000","DOI":"10.21437\/ICSLP.2000-3"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB11","first-page":"333","article-title":"Automatic extraction of F0 control rules using statistical analysis","volume":"28","author":"Hirai","year":"1996","journal-title":"Prog. Speech Synth."},{"key":"10.1016\/S0167-6393(02)00177-2_BIB12","unstructured":"Hirose, K., Fujisaki, H., 1993. A system for the synthesis of high-quality speech from texts on general weather conditions. IEICE Trans. Fundam. E-76-A, 11, 1971\u20131980"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB13","unstructured":"Hirst, D., Nicolas, P., Espesser, R., 1991. Coding the F0 of a continuous text in French: An experimental approach. In: Proc. Int. Congress on Phonetic Sciences 5. pp. 234\u2013237"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB14","doi-asserted-by":"crossref","unstructured":"Holm, B., Bailly, G., 2000. Generating prosody by suporposing multi-parametric overlapping contours. Proc. ICSLP\u20192000","DOI":"10.21437\/ICSLP.2000-513"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB15","doi-asserted-by":"crossref","unstructured":"Imai, S., 1978. Low bit rate cepstral vocoder using the log magnitude approximation filter. In: Proc. of ICASSP\u201978, pp. 441\u2013444","DOI":"10.1109\/ICASSP.1978.1170446"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB16","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0167-6393(99)00008-4","article-title":"Rules for the generation of ToBI-based American English intonation","volume":"28","author":"Jilka","year":"1999","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(02)00177-2_BIB17","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/S0167-6393(00)00065-0","article-title":"Generating prosodic attitudes in French: Data, model and evaluation","volume":"33","author":"Morlec","year":"2001","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(02)00177-2_BIB18","unstructured":"M\u00fcller, A.F., Zimmermann, H.G., Neuneier, R., 2000. Robust generation of symbolic prosody by a neural classifier based on autoassociators. ICASSP\u20192000"},{"issue":"4","key":"10.1016\/S0167-6393(02)00177-2_BIB19","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1121\/1.387033","article-title":"Synthesizing intonation","volume":"70","author":"Pierrehumbert","year":"1981","journal-title":"J. Acoust. Soc. Amer."},{"issue":"7","key":"10.1016\/S0167-6393(02)00177-2_BIB20","first-page":"849","article-title":"Accentuation rules for Japanese word concatenation","author":"Sagisaka","year":"1983","journal-title":"J. IEICE J66-D"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB21","doi-asserted-by":"crossref","unstructured":"Silverman, K., Beckman, M., Pitrelli, J., Ostendorf, M., Wightman, C., Price, P., Pierrehumbert, J., Hirschberg, J., 1992. TOBI: a standard for labeling English prosody. In: Proc. ICSLP\u201992. pp. 867\u2013870","DOI":"10.21437\/ICSLP.1992-260"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB22","unstructured":"Takeda, K., Sagisaka, N., Katagiri, S., Abe, M., Kurihara, H., 1988. Research Japanese Speech Database User\u2019s Manual"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB23","series-title":"Talking Machines: Theories, Models, and Designs","first-page":"287","article-title":"F0 generation with a data base of natural F0 patterns and with a neural network","author":"Traber","year":"1992"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB24","unstructured":"University of Stuttgart, Stuttgart Neural Network Simulator\u2013\u2013User Manual\u2013\u2013Version 4.1\u2013\u2013Report no. 6\/95 (1995)"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB25","unstructured":"van Santen, J.P.H., Pols, L.C.W., Abe, M., Kahn, D., Keller, E., Vonwiller, J., 1998. Report on the 3rd ESCA TTS Workshop Evaluation Procedure. In: Proc. of the 3rd ESCA\/COCOSDA Intern. Workshop on Speech Synthesis. pp. 329\u2013332"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB26","doi-asserted-by":"crossref","unstructured":"Venditti, J., Santen, J.V., 2000. Japanese intonation synthesis using superposition and linear alignment models. Proc. ICSLP\u20192000","DOI":"10.21437\/ICSLP.2000-150"},{"key":"10.1016\/S0167-6393(02)00177-2_BIB27","doi-asserted-by":"crossref","unstructured":"Widera, C., Portele, T., Wolters, M., 1999. Prediction of word prominence, Eurospeech\u201999. pp. 999\u20131002","DOI":"10.21437\/Eurospeech.1997-352"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639302001772?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639302001772?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T14:42:31Z","timestamp":1733928151000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639302001772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,6]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2003,6]]}},"alternative-id":["S0167639302001772"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(02)00177-2","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2003,6]]}}}