{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:29:18Z","timestamp":1776094158651,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,11,9]],"date-time":"2016-11-09T00:00:00Z","timestamp":1478649600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004281","name":"Narodowe Centrum Nauki","doi-asserted-by":"publisher","award":["DEC-2011\/03\/D\/ST6\/00914"],"award-info":[{"award-number":["DEC-2011\/03\/D\/ST6\/00914"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005632","name":"Narodowe Centrum Bada\u0144 i Rozwoju","doi-asserted-by":"publisher","award":["072\/R\/ID1\/2013\/03"],"award-info":[{"award-number":["072\/R\/ID1\/2013\/03"]}],"id":[{"id":"10.13039\/501100005632","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005632","name":"Narodowe Centrum Bada\u0144 i Rozwoju","doi-asserted-by":"publisher","award":["LIDER\/37\/69\/L-3\/11\/NCBR\/2012"],"award-info":[{"award-number":["LIDER\/37\/69\/L-3\/11\/NCBR\/2012"]}],"id":[{"id":"10.13039\/501100005632","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Akademia G\u00f3rniczo-Hutnicza im. Stanislawa Staszica (PL)","award":["15.11.230.252"],"award-info":[{"award-number":["15.11.230.252"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13636-016-0096-7","type":"journal-article","created":{"date-parts":[[2016,11,9]],"date-time":"2016-11-09T11:52:32Z","timestamp":1478692352000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Structure of pauses in speech in the context of speaker verification and classification of speech type"],"prefix":"10.1186","volume":"2016","author":[{"given":"Magdalena","family":"Igras-Cybulska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bartosz","family":"Zi\u00f3\u0142ko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"\u017belasko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcin","family":"Witkowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,9]]},"reference":[{"issue":"2","key":"96_CR1","first-page":"115","volume":"2","author":"F Batista","year":"2012","unstructured":"F Batista, H Moniz, I Trancoso, N Mamede, A Mata, Extending automatic transcripts in a unified data representation towards a prosodic-based metadata annotation and evaluation. Journal of Speech Sciences 2(2), 115\u2013138 (2012)","journal-title":"Journal of Speech Sciences"},{"key":"96_CR2","doi-asserted-by":"publisher","unstructured":"M Igras, B Zi\u00f3\u0142ko: Wavelet method for breath detection in audio signals. In: IEEE International Conference on Multimedia and Expo (ICME 2013), San Jose (2013). doi: 10.1109\/ICME.2013.6607428","DOI":"10.1109\/ICME.2013.6607428"},{"key":"96_CR3","volume-title":"Speech rate, pause and linguistic variation: an examination through the sociolinguistic archive and analysis project. Doctoral dissertation","author":"T Kendall","year":"2009","unstructured":"T Kendall, Speech rate, pause and linguistic variation: an examination through the sociolinguistic archive and analysis project. Doctoral dissertation (Duke University, Durham, 2009)"},{"key":"96_CR4","doi-asserted-by":"crossref","unstructured":"E Campione, J V\u00e9ronis.(2002). A large-scale multilingual study of silent pause duration. In: Proceedings of the Speech Prosody Conference, 199\u2013202","DOI":"10.21437\/SpeechProsody.2002-35"},{"key":"96_CR5","unstructured":"M Demol, W Verhelst, P Verhoeve. (2006). A study of speech pauses for multilingual time-scaling applications. In: Proc. ISCA-ITRW Multiling, (Stellenbosch, South Africa)."},{"issue":"9","key":"96_CR6","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1113\/expphysiol.2008.042424","volume":"93","author":"I Homma","year":"2008","unstructured":"I Homma, Y Masaoka, Breathing rhythms and emotions. Experimental physiology 93(9), 1011\u20131021 (2008)","journal-title":"Experimental physiology"},{"issue":"2","key":"96_CR7","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1164\/rccm.167.2.211","volume":"167","author":"American Thoracic Society and American College of Chest Physicians","year":"2003","unstructured":"American Thoracic Society and American College of Chest Physicians, ATS\/ACCP Statement on cardiopulmonary exercise testing. American Journal of Respiratory and Critical Care Medicine 167(2), 211\u2013277 (2003)","journal-title":"American Journal of Respiratory and Critical Care Medicine"},{"key":"96_CR8","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1016\/j.medengphy.2010.07.013","volume":"32","author":"V Rapcan","year":"2010","unstructured":"V Rapcan, S D\u2019Arcy, S Yeap, N Afzal, J Thakore, RB Reilly, Acoustic and temporal analysis of speech: a potential biomarker for schizophrenia. Medical Engineering & Physics 32, 1074\u20131079 (2010)","journal-title":"Medical Engineering & Physics"},{"key":"96_CR9","doi-asserted-by":"crossref","unstructured":"D Baron, E Shriberg, A Stolcke. (2002). Automatic punctuation and disfluency detection in multi-party meetings using prosodic and lexical cues. In: Proceedings of the International Conference on Spoken Language Processing, 949\u2013952","DOI":"10.21437\/ICSLP.2002-315"},{"issue":"1\u20132","key":"96_CR10","first-page":"127","volume":"32","author":"E Shriberg","year":"2000","unstructured":"E Shriberg, A Stolcke, D Hakkani- T\u00fcr, G T\u00fcr, Prosody-based automatic segmentation of speech into sentences and topics. Journal Speech Communication - Special issue on accessing information in spoken audio archive 32(1\u20132), 127\u2013154 (2000)","journal-title":"Journal Speech Communication - Special issue on accessing information in spoken audio archive"},{"key":"96_CR11","volume-title":"Trends in speech recognition","author":"WA Lea","year":"1980","unstructured":"WA Lea, Trends in speech recognition (Academic Press, New York, 1980)"},{"key":"96_CR12","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1121\/1.3213452","volume":"126","author":"V Ramanarayanan","year":"2009","unstructured":"V Ramanarayanan, E Bresch, D Byrd, L Goldstein, SS Narayanan, Analysis of pausing behavior in spontaneous speech using real-time magnetic resonance imaging of articulation. The Journal of the Acoustical Society of America 126, 160\u2013165 (2009)","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"1","key":"96_CR13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"T Kinnunen, H Li, An overview of text-independent speaker recognition: from features to supervectors. Speech communication 52(1), 12\u201340 (2010)","journal-title":"Speech communication"},{"issue":"4","key":"96_CR14","first-page":"25","volume":"4","author":"B Zi\u00f3\u0142ko","year":"2011","unstructured":"B Zi\u00f3\u0142ko, W Koz\u0142owski, M Zi\u00f3\u0142ko, R Samborski, D Sierra, J Ga\u0142ka, Hybrid wavelet-Fourier-HMM speaker recognition. International Journal of Hybrid Information Technology 4(4), 25\u201341 (2011)","journal-title":"International Journal of Hybrid Information Technology"},{"key":"96_CR15","series-title":"Speaker Classification I. Lecture Notes in Computer Science \/ Artificial Intelligence","first-page":"241","volume-title":"Higher-level features in speaker recognition","author":"E Shriberg","year":"2007","unstructured":"E Shriberg, Higher-level features in speaker recognition. Speaker Classification I. Lecture Notes in Computer Science \/ Artificial Intelligence (Springer, Berlin\/Heidelberg, 2007), pp. 241\u2013259"},{"key":"96_CR16","doi-asserted-by":"publisher","unstructured":"B Peskin, J Navratil, J Abramson, D Klusacek, DA Reynolds, X Bing: Using prosodic and conversational features for high-performance speaker recognition: report from JHU WS'02. IEEE International Conference on Acoustics, Speech, and Signal Processing (2003). doi: 10.1109\/ICASSP.2003.1202762","DOI":"10.1109\/ICASSP.2003.1202762"},{"key":"96_CR17","doi-asserted-by":"crossref","unstructured":"K S\u00f6nmez, E Shriberg, L Heck, M Weintraub. (1998). Modeling dynamic prosodic variation for speaker verification. In: Proc. ICSLP, 3189\u20133192","DOI":"10.21437\/ICSLP.1998-254"},{"issue":"4","key":"96_CR18","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.specom.2007.02.005","volume":"49","author":"G Adami","year":"2007","unstructured":"G Adami, Modeling prosodic differences for speaker recognition. Speech Communication 49(4), 277\u2013291 (2007)","journal-title":"Speech Communication"},{"key":"96_CR19","doi-asserted-by":"publisher","unstructured":"M Backes, G Doychev, M D\u00fcrmuth, B K\u00f6pf. (2010). Speaker recognition in encrypted voice streams. In: Proceedings of the 15th European Conference on Research in Computer Security, 508\u2013523","DOI":"10.1007\/978-3-642-15497-3_31"},{"key":"96_CR20","doi-asserted-by":"crossref","unstructured":"J L\u00f6\u00f6f, C Gollan, H Ney. (2009). Cross-language bootstrapping for unsupervised acoustic model training: rapid development of a Polish speech recognition system. In: Proceedings of Interspeech, Brighton, 88\u201391","DOI":"10.21437\/Interspeech.2009-20"},{"issue":"1\u20133","key":"96_CR21","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"DA Reynolds, TF Quatieri, RB Dunn, Speaker verification using adapted Gaussian mixture models. Digital Signal Processing 10(1\u20133), 19\u201341 (2000)","journal-title":"Digital Signal Processing"},{"key":"96_CR22","unstructured":"J Pelecanos, S Sridharan: Feature warping for robust speaker verification. In: Proc. Speaker Odyssey: the Speaker Recognition Workshop (Odyssey 2001), Crete, Greece, 213\u2013218 (2001)"},{"key":"96_CR23","series-title":"Models and analysis of vocal emissions for biomedical applications: 8th international workshop","first-page":"197","volume-title":"Different types of pauses as a source of information for biometry","author":"M Igras","year":"2013","unstructured":"M Igras, B Zi\u00f3\u0142ko, Different types of pauses as a source of information for biometry. Models and analysis of vocal emissions for biomedical applications: 8th international workshop (Firenze University Press, Firenze, 2013), pp. 197\u2013200"},{"issue":"1\u20132","key":"96_CR24","first-page":"3","volume":"32","author":"K Barczewska","year":"2013","unstructured":"K Barczewska, M Igras, Detection of disfluencies in speech signal. Challenges of modern technology 32(1\u20132), 3\u201310 (2013)","journal-title":"Challenges of modern technology"},{"key":"96_CR25","doi-asserted-by":"publisher","unstructured":"F Beritelli, A Spadaccini. (2012). Performance evaluation of automatic speaker recognition techniques for forensic applications. New Trends and Developments in Biometrics, 129\u2013148","DOI":"10.5772\/52000"},{"issue":"3","key":"96_CR26","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.specom.2005.02.018","volume":"46","author":"E Shriberg","year":"2005","unstructured":"E Shriberg, L Ferrer, S Kajarekar, A Venkataraman, A Stolcke, Modeling prosodic feature sequences for speaker recognition. Speech Communication 46(3), 455\u2013472 (2005)","journal-title":"Speech Communication"},{"key":"96_CR27","first-page":"41","volume-title":"Fundamentals of speech synthesis and speech recognition","author":"B Zellner","year":"1994","unstructured":"B Zellner, Pauses and the temporal structure of speech, in Fundamentals of speech synthesis and speech recognition, ed. by E Keller (Wiley, Chichester, 1994), pp. 41\u201362"},{"key":"96_CR28","doi-asserted-by":"crossref","unstructured":"E Shriberg: Spontaneous speech: How people really talk and why engineers should care. Proceedings of European Conference on Speech Communication and Technology, Eurospeech, 1781\u20131784 (2005)","DOI":"10.21437\/Interspeech.2005-3"},{"key":"96_CR29","unstructured":"B. Zi\u00f3\u0142ko, T. Jadczyk, D. Skurzok, P. \u017belasko, J. Ga\u0142ka, T. P\u0119dzim\u0105\u017c, I. Gawlik, S. Pa\u0142ka .2015. \u201cSARMATA 2.0 Automatic Polish Language Speech Recognition System\u201d, Interspeech, Dresden,"},{"key":"96_CR30","unstructured":"P Kenny. (2012). A small footprint i-vector extractor. Odyssey 2012: 1\u20136"},{"key":"96_CR31","unstructured":"https:\/\/sites.google.com\/site\/bosaristoolkit\/ Accessed: 30 May 2016"},{"key":"96_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2013.07.007","volume":"56","author":"R Dufour","year":"2014","unstructured":"R Dufour, Y Est\u00e8ve, P Del\u00e9glise, Characterizing and detecting spontaneous speech: application to speaker role recognition. Speech Communication 56, 1\u201318 (2014)","journal-title":"Speech Communication"},{"issue":"2","key":"96_CR33","first-page":"23","volume":"5","author":"A T\u00f3th","year":"2011","unstructured":"A T\u00f3th, Speech disfluencies in simultaneous interpreting: a mirror on cognitive processes. SKASE Journal of Translation and Interpretation 5(2), 23\u201331 (2011)","journal-title":"SKASE Journal of Translation and Interpretation"},{"key":"96_CR34","first-page":"103","volume":"10","author":"B Tissi","year":"2000","unstructured":"B Tissi, Silent pauses and disfluencies in simultaneous interpretation: a descriptive analysis. The Interpreters\u2019 Newsletter 10, 103\u2013127 (2000)","journal-title":"The Interpreters\u2019 Newsletter"},{"key":"96_CR35","unstructured":"L Ten Bosch, N. Oostdijk, J P De Ruiter. (2004). Turn-taking in social talk dialogues: temporal, formal and functional aspects. In 9th International Conference Speech and Computer (SPECOM'2004). 454\u2013461"},{"key":"96_CR36","doi-asserted-by":"publisher","unstructured":"J H Friedman, Greedy function approximation: a gradient boosting machine. Annals of statistics, 29(5),\u00a01189\u20131232\u00a0(2001)","DOI":"10.1214\/aos\/1013203451"},{"key":"96_CR37","unstructured":"Pedregosa et al. (2011). Scikit-learn: Machine Learning in Python, JMLR 12, pp. 2825\u20132830"},{"key":"96_CR38","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s10579-015-9302-y","volume":"50","author":"P \u017belasko","year":"2016","unstructured":"P \u017belasko, B Zi\u00f3\u0142ko, T Jadczyk, D Skurzok, \u201cAGH Corpus of Polish Speech\u201d. Language Resources and Evaluation 50, 585\u2013601 (2016)","journal-title":"Language Resources and Evaluation"},{"key":"96_CR39","volume-title":"\u201cThe DET curve in assessment of detection task performance\u201d, in Proceedings of the 5th European Conference on Speech Communication and Technology","author":"A Martin","year":"1997","unstructured":"A Martin, G Doddington, T Kamm, M Ordowski, M Przybocki, \u201cThe DET curve in assessment of detection task performance\u201d, in Proceedings of the 5th European Conference on Speech Communication and Technology (Greece, EUROSPEECH, Rhodes, 1997). pp. 1895\u20131898"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-016-0096-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-016-0096-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-016-0096-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T13:16:07Z","timestamp":1718889367000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-016-0096-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,9]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["96"],"URL":"https:\/\/doi.org\/10.1186\/s13636-016-0096-7","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,9]]},"article-number":"18"}}