{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T16:03:22Z","timestamp":1749657802812,"version":"3.41.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,12,2]],"date-time":"2015-12-02T00:00:00Z","timestamp":1449014400000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s10772-015-9327-z","type":"journal-article","created":{"date-parts":[[2015,12,2]],"date-time":"2015-12-02T04:21:13Z","timestamp":1449030073000},"page":"95-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Automatic prosodic tone choice classification with Brazil\u2019s intonation model"],"prefix":"10.1007","volume":"19","author":[{"given":"David O.","family":"Johnson","sequence":"first","affiliation":[]},{"given":"Okim","family":"Kang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,12,2]]},"reference":[{"issue":"3","key":"9327_CR1","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.bspc.2008.11.002","volume":"4","author":"O Amir","year":"2009","unstructured":"Amir, O., Wolf, M., & Amir, N. (2009). A clinical comparison between two acoustic analysis softwares: MDVP and Praat. Biomedical Signal Processing and Control, 4(3), 202\u2013205.","journal-title":"Biomedical Signal Processing and Control"},{"key":"9327_CR2","doi-asserted-by":"crossref","unstructured":"Ananthakrishnan, S., & Narayanan, S. (2008). Fine-grained pitch accent and boundary tone labeling with parametric f0 features. In IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. (pp. 4545\u20134548). IEEE.","DOI":"10.1109\/ICASSP.2008.4518667"},{"key":"9327_CR3","unstructured":"Beckman, M., & Elam, G. (1997). Guidelines for ToBI labelling. Available online: http:\/\/www.ling.ohio-state.edu\/research\/phonetics\/E_ToBI ."},{"key":"9327_CR4","doi-asserted-by":"crossref","unstructured":"Bocklet, T., & Shriberg, E. (2009). Speaker recognition using syllable-based constraints for cepstral frame selection. In IEEE International Conference on Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. (pp. 4525\u20134528). IEEE.","DOI":"10.1109\/ICASSP.2009.4960636"},{"key":"9327_CR5","unstructured":"Boersma, P., & Weenink, D. (2014). Praat: Doing phonetics by computer (version 5.3.83). [Computer program]. Retrieved August 19, 2014."},{"key":"9327_CR6","volume-title":"The communicative value of intonation in English","author":"D Brazil","year":"1997","unstructured":"Brazil, D. (1997). The communicative value of intonation in English. Cambridge: Cambridge University Press."},{"key":"9327_CR7","doi-asserted-by":"crossref","unstructured":"Breen, M., Dilley, L. C., Kraemer, J., & Gibson, E. (2012). Inter-transcriber reliability for two systems of prosodic annotation: ToBI (Tones and Break Indices) and RaP (Rhythm and Pitch).","DOI":"10.1515\/cllt-2012-0011"},{"key":"9327_CR8","doi-asserted-by":"crossref","unstructured":"Caruana, R., & Niculescu-Mizil, A. (2006). An empirical comparison of supervised learning algorithms. In Proceedings of the 23rd international conference on Machine learning (pp. 161\u2013168). ACM, New York.","DOI":"10.1145\/1143844.1143865"},{"key":"9327_CR9","doi-asserted-by":"crossref","unstructured":"Cauldwell, R. (2012). Brazil, David. The encyclopedia of applied linguistics.","DOI":"10.1002\/9781405198431.wbeal0108"},{"key":"9327_CR10","doi-asserted-by":"crossref","DOI":"10.1075\/lllt.1","volume-title":"Discourse intonation in L2: From theory and research to practice (Vol. 1)","author":"DM Chun","year":"2002","unstructured":"Chun, D. M. (2002). Discourse intonation in L2: From theory and research to practice (Vol. 1). Philadelphia, PA: John Benjamins Publishing."},{"issue":"1","key":"9327_CR11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37\u201346.","journal-title":"Educational and Psychological Measurement"},{"issue":"1","key":"9327_CR12","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.rasd.2011.03.012","volume":"6","author":"JJ Diehl","year":"2012","unstructured":"Diehl, J. J., & Paul, R. (2012). Acoustic differences in the imitation of prosodic patterns in children with autism spectrum disorders. Research in Autism Spectrum Disorders, 6(1), 123\u2013134.","journal-title":"Research in Autism Spectrum Disorders"},{"key":"9327_CR13","unstructured":"Dilley, L. C. (2005). The phonetics and phonology of tonal systems (Doctoral dissertation, Massachusetts Institute of Technology)."},{"key":"9327_CR14","unstructured":"Dilley, L. C., & Brown, M. (2005). The RaP (Rhythm and Pitch) Labeling System. Unpublished manuscript."},{"issue":"3","key":"9327_CR15","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.specom.2007.01.008","volume":"49","author":"D Escudero-Mancebo","year":"2007","unstructured":"Escudero-Mancebo, D., & Carde\u00f1oso-Payo, V. (2007). Applying data mining techniques to corpus based prosodic modeling. Speech Communication, 49(3), 213\u2013229.","journal-title":"Speech Communication"},{"issue":"1","key":"9327_CR16","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.csl.2013.08.001","volume":"28","author":"D Escudero-Mancebo","year":"2014","unstructured":"Escudero-Mancebo, D., Gonz\u00e1lez-Ferreras, C., Vivaracho-Pascual, C., & Carde\u00f1oso-Payo, V. (2014). A fuzzy classifier to deal with similarity between labels on automatic prosodic labeling. Computer Speech and Language, 28(1), 326\u2013341.","journal-title":"Computer Speech and Language"},{"issue":"5","key":"9327_CR17","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1111\/j.1469-7610.1991.tb01901.x","volume":"32","author":"J Fine","year":"1991","unstructured":"Fine, J., Bartolucci, G., Ginsberg, G., & Szatmari, P. (1991). The use of intonation to communicate in pervasive developmental disorders. Journal of Child Psychology and Psychiatry, 32(5), 771\u2013782.","journal-title":"Journal of Child Psychology and Psychiatry"},{"issue":"1315","key":"9327_CR18","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1098\/rstb.1994.0133","volume":"346","author":"U Frith","year":"1994","unstructured":"Frith, U., & Happ\u00e9, F. (1994). Language and communication in autistic disorders. Philosophical Transactions of the Royal Society B, 346(1315), 97\u2013104.","journal-title":"Philosophical Transactions of the Royal Society B"},{"key":"9327_CR19","unstructured":"Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., & Pallett, D. S. (1993). DARPA TIMIT acoustic-phonetic continuos speech corpus CD-ROM. NIST speech disc 1-1.1. NASA STI\/Recon Technical Report N, 93, 27403."},{"issue":"7","key":"9327_CR20","doi-asserted-by":"crossref","first-page":"2045","DOI":"10.1109\/TASL.2012.2194284","volume":"20","author":"C Gonz\u00e1lez-Ferreras","year":"2012","unstructured":"Gonz\u00e1lez-Ferreras, C., Escudero-Mancebo, D., Vivaracho-Pascual, C., & Carde\u00f1oso-Payo, V. (2012). Improving automatic classification of prosodic events by pairwise coupling. IEEE Transactions on Audio, Speech and Language Processing, 20(7), 2045\u20132058.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"2","key":"9327_CR21","first-page":"3","volume":"2007","author":"A H\u00e4m\u00e4l\u00e4inen","year":"2007","unstructured":"H\u00e4m\u00e4l\u00e4inen, A., Boves, L., de Veth, J., & Bosch, L. T. (2007). On the utility of syllable-based acoustic models for pronunciation variation modelling. EURASIP Journal on Audio, Speech, and Music Processing, 2007(2), 3.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"issue":"2","key":"9327_CR22","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1214\/aos\/1028144844","volume":"26","author":"T Hastie","year":"1998","unstructured":"Hastie, T., & Tibshirani, R. (1998). Classification by pairwise coupling. The Annals of Statistics, 26(2), 451\u2013471.","journal-title":"The Annals of Statistics"},{"issue":"2","key":"9327_CR23","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.system.2010.01.005","volume":"38","author":"O Kang","year":"2010","unstructured":"Kang, O. (2010). Relative salience of suprasegmental features on judgments of L2 comprehensibility and accentedness. System, 38(2), 301\u2013315.","journal-title":"System"},{"issue":"4","key":"9327_CR24","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1111\/j.1540-4781.2010.01091.x","volume":"94","author":"O Kang","year":"2010","unstructured":"Kang, O., Rubin, D., & Pickering, L. (2010). Suprasegmental measures of accentedness and judgments of language learner proficiency in oral English. The Modern Language Journal, 94(4), 554\u2013566.","journal-title":"The Modern Language Journal"},{"key":"9327_CR25","unstructured":"Kang, O., & Wang, L. (2014). Impact of different task types on candidates\u2019 speaking performances and interactive features that distinguish between CEFR levels. ISSN 1756-509X, 40."},{"key":"9327_CR26","volume-title":"Multi-Speech and CSL Software","author":"KayPENTAX","year":"2008","unstructured":"KayPENTAX. (2008). Multi-Speech and CSL Software. Lincoln Park, NJ: KayPENTAX."},{"key":"9327_CR27","doi-asserted-by":"crossref","unstructured":"Levow, G. A. (2005). Context in multi-lingual tone and pitch accent recognition. In INTERSPEECH (pp. 1809\u20131812).","DOI":"10.21437\/Interspeech.2005-552"},{"key":"9327_CR28","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, S., Li, M., Lo, W. K., & Meng, H. (2010). Detection of intonation in L2 English speech of native Mandarin learners. In 2010 7th International Symposium on Chinese Spoken Language Processing (ISCSLP) (pp. 69\u201374). IEEE.","DOI":"10.1109\/ISCSLP.2010.5684846"},{"key":"9327_CR29","unstructured":"Litman, D. J., Hirschberg, J. B., & Swerts, M. (2000). Predicting automatic speech recognition performance using prosodic cues. In Proceedings of the 1st North American chapter of the association for computational linguistics conference (pp. 218\u2013225). Association for Computational Linguistics."},{"issue":"4","key":"9327_CR30","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1159\/000227999","volume":"61","author":"Y Maryn","year":"2009","unstructured":"Maryn, Y., Corthals, P., De Bodt, M., Van Cauwenberge, P., & Deliyski, D. (2009). Perturbation measures of voice: a comparative study between Multi-Dimensional Voice Program and Praat. Folia Phoniatrica et Logopaedica, 61(4), 217\u2013226.","journal-title":"Folia Phoniatrica et Logopaedica"},{"key":"9327_CR31","unstructured":"MathWorks, Inc. (2013). MATLAB Release 2013a. [Computer program]. Retrieved February 15, 2013."},{"issue":"4","key":"9327_CR32","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1080\/1368282031000154204","volume":"38","author":"J McCann","year":"2003","unstructured":"McCann, J., & Pepp\u00e9, S. (2003). Prosody in autism spectrum disorders: a critical review. International Journal of Language and Communication Disorders, 38(4), 325\u2013350.","journal-title":"International Journal of Language and Communication Disorders"},{"issue":"30","key":"9327_CR33","doi-asserted-by":"crossref","first-page":"13354","DOI":"10.1073\/pnas.1003882107","volume":"107","author":"DK Oller","year":"2010","unstructured":"Oller, D. K., Niyogi, P., Gray, S., Richards, J. A., Gilkerson, J., Xu, D., & Warren, S. F. (2010). Automated vocal analysis of naturalistic recordings from children with autism, language delay, and typical development. Proceedings of the National Academy of Sciences, 107(30), 13354\u201313359.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"9327_CR34","unstructured":"Ostendorf, M. (1999). Moving beyond the \u2018beads-on-a-string\u2019model of speech. In Proceedings of IEEE ASRU Workshop (pp. 79\u201384). Piscataway, NJ: IEEE."},{"key":"9327_CR35","unstructured":"Ostendorf, M., Price, P. J., & Shattuck-Hufnagel, S. (1995). The Boston University radio news corpus. Linguistic Data Consortium, 1\u201319."},{"issue":"2","key":"9327_CR36","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/s10803-004-1999-1","volume":"35","author":"R Paul","year":"2005","unstructured":"Paul, R., Augustyn, A., Klin, A., & Volkmar, F. R. (2005). Perception and production of prosody by speakers with autism spectrum disorders. Journal of Autism and Developmental Disorders, 35(2), 205\u2013220.","journal-title":"Journal of Autism and Developmental Disorders"},{"key":"9327_CR37","unstructured":"Pickering, L. (1999). An analysis of prosodic systems in the classroom discourse of native speaker and nonnative speaker teaching assistants. Unpublished doctoral dissertation: Gainesville: University of Florida."},{"key":"9327_CR38","unstructured":"Pierrehumbert, J. B. (1980). The phonology and phonetics of English intonation (Doctoral dissertation, Massachusetts Institute of Technology)."},{"issue":"5","key":"9327_CR39","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1109\/TASL.2010.2090147","volume":"19","author":"F Ringeval","year":"2011","unstructured":"Ringeval, F., Demouy, J., Szaszak, G., Chetouani, M., Robel, L., Xavier, J., & Plaza, M. (2011). Automatic intonation recognition for the prosodic assessment of language-impaired children. IEEE Transactions on Audio, Speech, and Language Processing, 19(5), 1328\u20131342.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9327_CR40","unstructured":"Rosenberg, A. (2010). Classification of prosodic events using quantized contour modeling. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics (pp. 721\u2013724). Association for Computational Linguistics."},{"key":"9327_CR41","doi-asserted-by":"crossref","unstructured":"Rosenberg, A. (2010). AutoBI-a tool for automatic toBI annotation. In INTERSPEECH (pp. 146\u2013149).","DOI":"10.21437\/Interspeech.2010-71"},{"key":"9327_CR42","doi-asserted-by":"crossref","unstructured":"Rosenberg, A. (2012). Modeling intensity contours and the interaction of pitch and intensity to improve automatic prosodic event detection and classification. In 2012 IEEE Spoken Language Technology Workshop (SLT) (pp. 376\u2013381). IEEE.","DOI":"10.1109\/SLT.2012.6424253"},{"issue":"3","key":"9327_CR43","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1006\/csla.1996.0010","volume":"10","author":"K Ross","year":"1996","unstructured":"Ross, K., & Ostendorf, M. (1996). Prediction of abstract prosodic labels for speech synthesis. Computer Speech and Language, 10(3), 155\u2013185.","journal-title":"Computer Speech and Language"},{"issue":"3","key":"9327_CR44","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.specom.2005.02.018","volume":"46","author":"E Shriberg","year":"2005","unstructured":"Shriberg, E., Ferrer, L., Kajarekar, S., Venkataraman, A., & Stolcke, A. (2005). Modeling prosodic feature sequences for speaker recognition. Speech Communication, 46(3), 455\u2013472.","journal-title":"Speech Communication"},{"issue":"5","key":"9327_CR45","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1044\/1092-4388(2001\/087)","volume":"44","author":"LD Shriberg","year":"2001","unstructured":"Shriberg, L. D., Paul, R., McSweeny, J. L., Klin, A., Cohen, D. J., & Volkmar, F. R. (2001). Speech and prosody characteristics of adolescents and adults with high-functioning autism and Asperger syndrome. Journal of Speech, Language, and Hearing Research, 44(5), 1097\u20131115.","journal-title":"Journal of Speech, Language, and Hearing Research"},{"key":"9327_CR46","doi-asserted-by":"crossref","unstructured":"Sun, X. (2002). Pitch accent prediction using ensemble machine learning. In INTERSPEECH.","DOI":"10.21437\/ICSLP.2002-316"},{"key":"9327_CR47","doi-asserted-by":"crossref","unstructured":"Syrdal, A. K., & McGory, J. T. (2000). Inter-transcriber reliability of ToBI prosodic labeling. In INTERSPEECH (pp. 235\u2013238).","DOI":"10.21437\/ICSLP.2000-521"},{"issue":"3","key":"9327_CR48","doi-asserted-by":"crossref","first-page":"1697","DOI":"10.1121\/1.428453","volume":"107","author":"P Taylor","year":"2000","unstructured":"Taylor, P. (2000). Analysis and synthesis of intonation using the tilt model. The Journal of the Acoustical Society of America, 107(3), 1697\u20131714.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9327_CR49","unstructured":"The Centre for Speech Technology Research, University of Edinburgh (2014), The Festival Speech Synthesis System, [Computer Program]. Retrieved September 15, 2014, from http:\/\/www.cstr.ed.ac.uk\/projects\/festival ."},{"issue":"3","key":"9327_CR50","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1177\/1362361310363281","volume":"14","author":"JP Santen Van","year":"2010","unstructured":"Van Santen, J. P., Prud\u2019hommeaux, E. T., Black, L. M., & Mitchell, M. (2010). Computational prosodic markers for autism. Autism, 14(3), 215\u2013236.","journal-title":"Autism"},{"key":"9327_CR51","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195143218.001.0001","volume-title":"The music of everyday speech: Prosody and discourse analysis","author":"A Wennerstrom","year":"2001","unstructured":"Wennerstrom, A. (2001). The music of everyday speech: Prosody and discourse analysis. New York: Oxford University Press."},{"key":"9327_CR52","unstructured":"Wightman, C., Price, P., Pierrehumbert, J., & Hirschberg, J. (1992). ToBI: A standard for labeling English prosody. In Proceedings of the 1992 International Conference on Spoken Language Processing, ICSLP (pp. 12\u201316)."},{"key":"9327_CR53","doi-asserted-by":"crossref","unstructured":"Xu, D., Gilkerson, J., Richards, J., Yapanel, U., & Gray, S. (2009, September). Child vocalization composition as discriminant information for automatic autism detection. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009. EMBC 2009. (pp. 2518\u20132522). Minneapolis: IEEE.","DOI":"10.1109\/IEMBS.2009.5334846"},{"key":"9327_CR54","first-page":"2729","volume-title":"Proceedings of the International Conference on Spoken Language Processing","author":"T Yoon","year":"2004","unstructured":"Yoon, T., Chavarria, S., Cole, J., & Hasegawa-Johnson, M. (2004). Intertranscriber reliability of prosodic labeling on telephone conversation using ToBI. Proceedings of the International Conference on Spoken Language Processing (pp. 2729\u20132732). Japan: Nara."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9327-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-015-9327-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9327-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T16:48:59Z","timestamp":1748710139000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-015-9327-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12,2]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["9327"],"URL":"https:\/\/doi.org\/10.1007\/s10772-015-9327-z","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2015,12,2]]}}}