{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:57Z","timestamp":1740098937566,"version":"3.37.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_39","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"398-406","source":"Crossref","is-referenced-by-count":1,"title":["Hesitations in Spontaneous Speech: Acoustic Analysis and Detection"],"prefix":"10.1007","author":[{"given":"Vasilisa","family":"Verkhodanova","sequence":"first","affiliation":[]},{"given":"Vladimir","family":"Shapranov","sequence":"additional","affiliation":[]},{"given":"Irina","family":"Kipyatkova","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"39_CR1","unstructured":"Department of Phonetics of Saint Petersburg University. http:\/\/phonetics.spbu.ru\/"},{"key":"39_CR2","unstructured":"Scikit-Learn: Machine learning in Python. http:\/\/scikit-learn.org"},{"issue":"1","key":"39_CR3","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1017\/S0332586500002092","volume":"13","author":"J Allwood","year":"1990","unstructured":"Allwood, J., Nivre, J., Ahls\u00e9n, E.: Speech management on the non-written life of speech. Nordic J. Linguist. 13(1), 3\u201348 (1990)","journal-title":"Nordic J. Linguist."},{"key":"39_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2, 1\u201327 (2011). http:\/\/www.csie.ntu.edu.tw\/cjlin\/libsvm","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"issue":"1","key":"39_CR5","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/S0010-0277(02)00017-3","volume":"84","author":"HH Clark","year":"2002","unstructured":"Clark, H.H., Tree, J.E.F.: Using uh and um in spontaneous speaking. Cognition 84(1), 73\u2013111 (2002)","journal-title":"Cognition"},{"key":"39_CR6","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511620539","volume-title":"Using Language","author":"H Clark","year":"1996","unstructured":"Clark, H.: Using Language. Cambridge University Press, Cambridge (1996)"},{"key":"39_CR7","unstructured":"Du Bois, J.W., Chafe, W.L., Meyer, C., Thompson, S.A., Martey, N.: Santa Barbara Corpus of Spoken American English, Linguistic Data Consortium. Philadelphia (2000\u20132005)"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE: the Munich versatile and fast open-source audio feature extractor. In: Proceeding of 18th ACM International Conference on Multimedia, pp. 1459\u20131462. ACM (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"39_CR9","unstructured":"Giannini, A.: Hesitation phenomena in spontaneous Italian. In: Proceeding of 15th International Congress of Phonetic Sciences, Barcelona, Spain, pp. 2653\u20132656 (2003)"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Holliman, E.C., McDaniel, J.: SwitchBoard: telephone speech corpus for research and development. In: Proceeding of International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1992), vol. 1, pp. 517\u2013520. IEEE (1992)","DOI":"10.1109\/ICASSP.1992.225858"},{"issue":"1","key":"39_CR11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1137\/1037001","volume":"37","author":"HJ Heijmans","year":"1995","unstructured":"Heijmans, H.J.: Mathematical morphology: a modern approach in image processing based on algebra and geometry. SIAM Rev. 37(1), 1\u201336 (1995)","journal-title":"SIAM Rev."},{"key":"39_CR12","unstructured":"INTERSPEECH: Computational Paralinguistic Challenge (2013). http:\/\/emotion-research.net\/sigs\/speech-sig\/is13-compare"},{"key":"39_CR13","unstructured":"Khurshudian, V.: Hesitation in typologically different languages: an experimental study. In: Proceeding of International Conference on Computational Linguistics Dialogue, pp. 497\u2013501 (2005)"},{"key":"39_CR14","unstructured":"Kibrik, A., Podlesskaya, V. (eds.): Rasskazy o Snovideniyah: Korpusnoye Issledovaniye Ustnogo Russkogo Diskursa [Night dream stories: Corpus study of Russian discourse]. Litres (2014)"},{"key":"39_CR15","first-page":"335","volume":"2013","author":"H Medeiros","year":"2013","unstructured":"Medeiros, H., Batista, F., Moniz, H., Trancoso, I., Meinedo, H.: Experiments on automatic detection of filled pauses using prosodic features. Actas de Inforum 2013, 335\u2013345 (2013)","journal-title":"Actas de Inforum"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Medeiros, H., Moniz, H., Batista, F., Trancoso, I., Nunes, L., et al.: Disfluency detection based on prosodic features for university lectures. In: Proceeding of INTERSPEECH 2013, Lyon, France, pp. 2629\u20132633 (2013)","DOI":"10.21437\/Interspeech.2013-605"},{"key":"39_CR17","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.specom.2014.05.004","volume":"65","author":"H Moniz","year":"2014","unstructured":"Moniz, H., Batista, F., Mata, A.I., Trancoso, I.: Speaking style effects in the production of disfluencies. Speech Commun. 65, 20\u201335 (2014)","journal-title":"Speech Commun."},{"key":"39_CR18","series-title":"Cognition and Language: A Series in Psycholinguistics","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77632-3","volume-title":"Communicating with One Another: Toward a Psychology of Spontaneous Spoken Discourse","author":"DC O\u2019Connel","year":"2009","unstructured":"O\u2019Connel, D.C., Kowal, S.: Communicating with One Another: Toward a Psychology of Spontaneous Spoken Discourse. Cognition and Language: A Series in Psycholinguistics. Springer Science & Business Media, New York (2009). doi: 10.1007\/978-0-387-77632-3"},{"issue":"6","key":"39_CR19","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1007\/s10936-004-2666-6","volume":"33","author":"D O\u2019Connell","year":"2004","unstructured":"O\u2019Connell, D., Kowal, S.: The history of research on the filled pause as evidence of the written language bias in linguistics. J. Psycholinguist. Res. 33(6), 459\u2013474 (2004)","journal-title":"J. Psycholinguist. Res."},{"issue":"1","key":"39_CR20","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1017\/S0025100301001116","volume":"31","author":"R Ogden","year":"2001","unstructured":"Ogden, R.: Turn-holding, turn-yielding and laryngeal activity in finnish talk-in-interaction. J. Int. Phonetics Assoc. 31(1), 139\u201352 (2001)","journal-title":"J. Int. Phonetics Assoc."},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"O\u2019Shaughnessy, D.: Recognition of hesitations in spontaneous speech. In: Proceeding of International Conference on Acoustics, Speech, and Signal Processing, (ICASSP-1992), vol. 1, pp. 521\u2013524. IEEE (1992)","DOI":"10.1109\/ICASSP.1992.225857"},{"key":"39_CR22","unstructured":"Ostendorf, M., Shriberg, E., Stolcke, A.: Human language technology: opportunities and challenges. Technical report, DTIC Document (2005)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Prylipko, D., Egorow, O., Siegert, I., Wendemuth, A.: Application of image processing methods to filled pauses detection from spontaneous speech. In: Proceeding of INTERSPEECH 2014, Singapore, pp. 1816\u20131820. ISCA (2014)","DOI":"10.21437\/Interspeech.2014-413"},{"issue":"1","key":"39_CR24","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.csl.2012.01.005","volume":"27","author":"R Ranganath","year":"2013","unstructured":"Ranganath, R., Jurafsky, D., McFarland, D.A.: Detecting friendly, flirtatious, awkward, and assertive speech in speed-dates. Comput. Speech Lang. 27(1), 89\u2013115 (2013)","journal-title":"Comput. Speech Lang."},{"key":"39_CR25","unstructured":"Shriberg, E.: Preliminaries to a theory of speech disfluencies. Ph.D. thesis, University of California at Berkeley (1994)"},{"issue":"1","key":"39_CR26","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1017\/S0025100301001128","volume":"31","author":"E Shriberg","year":"2001","unstructured":"Shriberg, E.: To \u2018Errrr\u2019 is human: ecology and acoustics of speech disfluencies. J. Int. Phonetic Assoc. 31(1), 153\u2013169 (2001)","journal-title":"J. Int. Phonetic Assoc."},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Shriberg, E., Bates, R.A., Stolcke, A.: A prosody only decision-tree model for disfluency detection. In: Proceeding of the Eurospeech 1997, 5th European Conference on Speech Communication and Technology, Rhodes, Greece, pp. 2383\u20132386 (1997)","DOI":"10.21437\/Eurospeech.1997-626"},{"key":"39_CR28","unstructured":"Stepanova, S.: Some features of filled hesitation pauses in spontaneous Russian. In: Proceeding of 16th International Congress of Phonetic Sciences, Saarbrucken, Germany, vol. 16, pp. 1325\u20131328 (2007)"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Shriberg, E., Bates, R.A., Ostendorf, M., Hakkani, D., Plauche, M., T\u00fcr, G., Lu, Y.: Automatic detection of sentence boundaries and disfluencies based on recognized words. In: ICSLP (1998)","DOI":"10.21437\/ICSLP.1998-486"},{"issue":"2\u20133","key":"39_CR30","first-page":"587","volume":"48","author":"ET Thordardottir","year":"2001","unstructured":"Thordardottir, E.T., Weismer, S.E.: Content mazes and filled pauses in narrative language samples of children with specific language impairment. Brain Cogn. 48(2\u20133), 587\u2013592 (2001)","journal-title":"Brain Cogn."},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Verkhodanova, V., Shapranov, V.: Automatic detection of filled pauses and lengthenings in the spontaneous Russian speech. In: Proceeding of 7th International Conference Speech Prosody, pp. 1110\u20131114 (2014)","DOI":"10.21437\/SpeechProsody.2014-211"},{"key":"39_CR32","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/978-3-319-23132-7_35","volume-title":"Speech and Computer","author":"V Verkhodanova","year":"2015","unstructured":"Verkhodanova, V., Shapranov, V.: Multi-factor method for detection of filled pauses and lengthenings in Russian spontaneous speech. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS (LNAI), vol. 9319, pp. 285\u2013292. Springer, Cham (2015). doi: 10.1007\/978-3-319-23132-7_35"},{"key":"39_CR33","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/978-3-319-43958-7_26","volume-title":"Speech and Computer","author":"V Verkhodanova","year":"2016","unstructured":"Verkhodanova, V., Shapranov, V.: Detecting filled pauses and lengthenings in Russian spontaneous speech using SVM. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 224\u2013231. Springer, Cham (2016). doi: 10.1007\/978-3-319-43958-7_26"},{"issue":"2","key":"39_CR34","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.specom.2007.06.002","volume":"50","author":"M Watanabe","year":"2008","unstructured":"Watanabe, M., Hirose, K., Den, Y., Minematsu, N.: Filled pauses as cues to the complexity of upcoming phrases for native and non-native listeners. Speech Commun. 50(2), 81\u201394 (2008)","journal-title":"Speech Commun."},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Zahorian, S.A., Wu, J., Karnjanadecha, M., Vootkur, C.S., Wong, B., Hwang, A., Tokhtamyshev, E.: Open-source multi-language audio database for spoken language processing applications. In: Proceeding of INTERSPEECH 2011, Florence, Italy, pp. 1493\u20131496 (2011)","DOI":"10.21236\/ADA571008"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:51:18Z","timestamp":1692924678000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}