{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:24:28Z","timestamp":1760131468225},"reference-count":33,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[2001,1,1]],"date-time":"2001-01-01T00:00:00Z","timestamp":978307200000},"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":[[2001,1]]},"DOI":"10.1016\/s0167-6393(00)00073-x","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"135-151","source":"Crossref","is-referenced-by-count":26,"title":["Automatic ToBI prediction and alignment to speed manual labeling of prosody"],"prefix":"10.1016","volume":"33","author":[{"given":"Ann K.","family":"Syrdal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julia","family":"Hirschberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julie","family":"McGory","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mary","family":"Beckman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"year":"1988","series-title":"The Awk Programming Language","author":"Aho","key":"10.1016\/S0167-6393(00)00073-X_BIB1"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB2","unstructured":"Beckman, M.E., Elam, G.A., 1997. Guidelines for ToBI labeling. Guidelines version 3.0, The Ohio State University Research Foundation"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB3","unstructured":"Beckman, M.E., Hirschberg, J., 1994. The ToBI annotation conventions. Appendix A. The Ohio State University Research Foundation"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB4","doi-asserted-by":"crossref","unstructured":"Beutnagel, M., Conkie, A., Schroeter, J., Stylianou, Y., Syrdal, A., 1999. The AT&T Next-Gen TTS System. In: Proceedings of the Joint Meeting of ASA, EAA, and DEGA, Paper 2aSCa4, Berlin, March 1999. J. Acoust. Soc. Amer. 105 (2), 1030 (A)","DOI":"10.1121\/1.424924"},{"year":"1984","series-title":"Classification and Regression Trees","author":"Breiman","key":"10.1016\/S0167-6393(00)00073-X_BIB5"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB6","doi-asserted-by":"crossref","unstructured":"Byrd, D., 1992. Sex, dialects, reduction. In: Ohala, J.J., Nearey, T.M., Derwing, B.L., Hodge, M.M., Wiebe, G.E. (Eds.), Proceedings of the International Conference on Spoken Language Processing, Banff, October 1992, ICSLP, pp. 827\u2013830","DOI":"10.21437\/ICSLP.1992-271"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB7","doi-asserted-by":"crossref","unstructured":"Conkie, A., Riccardi, G., Rose, R.C., 1999. Prosody recognition from speech utterances using acoustic and linguistic based models of prosodic events. In: Proceedings of the European Conference on Speech Communication and Technology. Budapest, September 1999, Eurospeech, ESCA. Vol. 1, pp. 523\u2013526","DOI":"10.21437\/Eurospeech.1999-135"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB8","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S. and Dahlgren, N.L., 1986. The DARPA TIMIT acoustic\u2013phonetic continuous speech corpus CDROM. CDROM, NIST [www.ldc.upenn.edu\/lol\/docs\/TIMIT.html]"},{"issue":"3","key":"10.1016\/S0167-6393(00)00073-X_BIB9","first-page":"175","article-title":"Attention, intentions, and the structure of discourse","volume":"12","author":"Grosz","year":"1986","journal-title":"Computational Linguistics"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB10","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/0004-3702(93)90020-C","article-title":"Pitch accent in context: predicting intonational prominence from text","volume":"63","author":"Hirschberg","year":"1993","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB11","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/0167-6393(96)00017-9","article-title":"Training intonational phrasing rules automatically for English and Spanish text-to-speech","volume":"18","author":"Hirschberg","year":"1996","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB12","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1121\/1.1906982","article-title":"The influence of consonant environment upon the secondary acoustical characteristics of vowels","volume":"25","author":"House","year":"1953","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(00)00073-X_BIB13","unstructured":"Kenyon, J.S., Knott, T.A., 1953. A Pronouncing Dictionary of American English. G. & C. Merriam, Springfield, MA"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB14","doi-asserted-by":"crossref","unstructured":"Ladd, D.R., 1979. Light and shadow: a study of the syntax and semantics of sentence accents in English. In: Waugh, L., van Coetsem, F. (Eds.), Contributions to Grammatical Studies: Semantics and Syntax. University Park Press, Baltimore, pp. 93\u2013131","DOI":"10.1163\/9789004657793_006"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1159\/000258062","article-title":"An acoustic phonetic study of internal open juncture","volume":"5","author":"Lehiste","year":"1960","journal-title":"Phonetica"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB16","unstructured":"Liberman, M., Sproat, R., 1992. The stress and structure of modified noun phrases in English. In: Sag, I. (Ed.), Lexical Matters. University of Chicago Press, Chicago"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB17","doi-asserted-by":"crossref","unstructured":"Litman, D., Hirschberg, J., 1990. Disambiguating cue phrases in text and speech. In: Proceedings of the 13th International Conference on Computational Linguistics. Helsinki, August 1990, COLING, pp. 251\u2013256","DOI":"10.3115\/997939.997983"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB18","doi-asserted-by":"crossref","unstructured":"Marcus, M.P., Santorini, B., Marcinkiewicz, M.A., 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics 19 (2), 313\u2013330 [www.cis.upenn.edu\/treebank\/home.html]","DOI":"10.21236\/ADA273556"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB19","doi-asserted-by":"crossref","unstructured":"McGory, J., Herman, R., Syrdal, A., 1999. Using tone similarity judgements in tests of intertranscriber reliability. J. Acoust. Soc. Amer. 106, 2242 (A)","DOI":"10.1121\/1.427641"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB20","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1159\/000261670","article-title":"What makes speakers omit pitch accents?: An experiment","volume":"39","author":"Nooteboom","year":"1982","journal-title":"Phonetica"},{"year":"1993","series-title":"Acoustics of American English Speech: A Dynamic Approach","author":"Olive","key":"10.1016\/S0167-6393(00)00073-X_BIB21"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB22","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1121\/1.1908183","article-title":"Duration of syllable nuclei in English","volume":"32","author":"Peterson","year":"1960","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(00)00073-X_BIB23","doi-asserted-by":"crossref","unstructured":"Pierrehumbert, J., Hirschberg, J., 1990. The meaning of intonation contours in the interpretation of discourse. In: Cohen, P., Morgan, J., Pollack, M. (Eds.), Plans and Intentions in Communications. MIT Press, Cambridge, pp. 271\u2013312","DOI":"10.7551\/mitpress\/3839.003.0016"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB24","doi-asserted-by":"crossref","unstructured":"Pitrelli, J., Beckman, M., Hirschberg, J., 1994. Evaluation of prosodic transcription labeling reliability in the ToBI framework. In: Proceedings of the Third International Conference on Spoken Language Processing. Yokohama, 1994, ICSLP. Vol. 2, pp. 123\u2013126","DOI":"10.21437\/ICSLP.1994-34"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB25","doi-asserted-by":"crossref","first-page":"2956","DOI":"10.1121\/1.401770","article-title":"The use of prosody in syntactic disambiguation","volume":"90","author":"Price","year":"1991","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(00)00073-X_BIB26","doi-asserted-by":"crossref","unstructured":"Prince, E.F., 1992. The ZPG letter: subjects, definiteness, and information-status. In: Thompson, S., Mann, W. (Eds.), Discourse Description: Diverse Analyses of a Fund Raising Text. John Benjamins B.V., Philadelphia, pp. 295\u2013325","DOI":"10.1075\/pbns.16.12pri"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB27","doi-asserted-by":"crossref","unstructured":"Silverman, K., Beckman, M., Pierrehumbert, J., Ostendorf, M., Wightman, C., Price, P., Hirschberg, J., 1992. ToBI: A standard scheme for labeling prosody. In: Proceedings of the Second International Conference on Spoken Language Processing. Banff, October 1992. ICSLP, pp. 867\u2013879","DOI":"10.21437\/ICSLP.1992-260"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB28","doi-asserted-by":"crossref","unstructured":"Sproat, R., Hirschberg, J., Yarowsky, D., 1992. A corpus-based synthesizer. In: Proceedings of the International Conference on Spoken Language Processing. Banff, October 1992, ICSLP, pp. 563\u2013566","DOI":"10.21437\/ICSLP.1992-130"},{"year":"1996","series-title":"Programming Perl","author":"Wall","key":"10.1016\/S0167-6393(00)00073-X_BIB29"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB30","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0885-2308(92)90025-Y","article-title":"Automatic classification of intonational phrase boundaries","volume":"6","author":"Wang","year":"1992","journal-title":"Computer Speech and Language"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB31","doi-asserted-by":"crossref","unstructured":"Waves+ Manual, 1996. Entropic Research Laboratory, Inc","DOI":"10.1016\/S0958-2118(00)88739-X"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB32","unstructured":"Wightman, C., 1999. Personal communication"},{"key":"10.1016\/S0167-6393(00)00073-X_BIB33","unstructured":"Wightman, C., Talkin, D., 1994. The aligner: A system for automatic time alignment of English text and speech. Document version 1.7, Entropic Research Laboratory, Inc"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763930000073X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S016763930000073X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T11:42:15Z","timestamp":1704109335000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S016763930000073X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,1]]},"references-count":33,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2001,1]]}},"alternative-id":["S016763930000073X"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(00)00073-x","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[2001,1]]}}}