{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:25:18Z","timestamp":1709324718408},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,7,25]],"date-time":"2014-07-25T00:00:00Z","timestamp":1406246400000},"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":["Soft Comput"],"published-print":{"date-parts":[[2015,1]]},"DOI":"10.1007\/s00500-014-1383-9","type":"journal-article","created":{"date-parts":[[2014,7,24]],"date-time":"2014-07-24T06:32:04Z","timestamp":1406183524000},"page":"47-59","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Topic segmentation on spoken documents using self-validated acoustic cuts"],"prefix":"10.1007","volume":"19","author":[{"given":"Hongjie","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lilei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,25]]},"reference":[{"key":"1383_CR1","doi-asserted-by":"crossref","unstructured":"Bamberg P, Chow Yl, Gillick L, Roth R, Sturtevant D (1990) The dragon continuous speech recognition system: a real-time implementation. In: Proceedings of DARPA Speech and Natural Language Workshop, pp 78\u201381","DOI":"10.3115\/116580.116610"},{"key":"1383_CR2","doi-asserted-by":"crossref","unstructured":"Banerjee S, Rudnicky IA (2006) A texttiling based approach to topic boundary detection in meetings. In: Proceedings of annual conference of the International Speech Communication Association (INTERSPEECH), ISCA, pp 57\u201360","DOI":"10.21437\/Interspeech.2006-15"},{"key":"1383_CR3","unstructured":"Beeferman D, Berger A, Lafferty J (1997) Text segmentation using exponential models. In: Proceedings of 2nd Conference of Empirical methods on natural language process. (EMNLP), pp 35\u201346"},{"issue":"1\u20133","key":"1383_CR4","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1007506220214","volume":"34","author":"D Beeferman","year":"1999","unstructured":"Beeferman D, Berger A, Lafferty J (1999) Statistical models for text segmentation. Mach Learn 34(1\u20133):177\u2013210","journal-title":"Mach Learn"},{"key":"1383_CR5","unstructured":"Blei DM, Moreno PJ (2001) Topic segmentation with an aspect hidden markov model. In: Proceedings of 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, pp 343\u2013348"},{"key":"1383_CR6","doi-asserted-by":"crossref","unstructured":"Brants T, Chen F, Tsochantaridis I (2002) Topic-based document segmentation with probabilistic latent semantic analysis. In: Proceedings of 12th International conference on information and knowledge management (CIKM), ACM, pp 211\u2013218","DOI":"10.1145\/584792.584829"},{"key":"1383_CR7","doi-asserted-by":"crossref","unstructured":"Chan SK, Xie L, Meng H (2007) Modeling the statistical behavior of lexical chains to capture word cohesiveness for automatic story segmentation. In: Proceedings of the annual conference of the International Speech Communication Association (INTERSPEECH), ISCA, pp 2581\u20132584","DOI":"10.21437\/Interspeech.2007-685"},{"key":"1383_CR8","unstructured":"Choi FYY (2000) Advances in domain independent linear text segmentation. In: Proceedings of the 1st North American Chapter of the Association for Computational Linguistics (NAACL)., ACL, pp 26\u201333"},{"issue":"4","key":"1383_CR9","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1137\/070710111","volume":"51","author":"A Clauset","year":"2009","unstructured":"Clauset A, Shalizi CR, Newman ME (2009) Power-law distributions in empirical data. SIAM Rev 51(4):661\u2013703","journal-title":"SIAM Rev"},{"key":"1383_CR10","unstructured":"Dharanipragada S, Franz M, Mccarley J, Roukos S, Ward T (1999) Story segmentation and topic detection in the broadcast news domain. In: Proceedings of the DARPA Broadcast News Workshop, pp 65\u201368"},{"key":"1383_CR11","unstructured":"Dredze M, Jansen A, Coppersmith G, Church K (2010) Nlp on spoken documents without asr. In: Proceedings of the conference on empirical methods on natural language processing (EMNLP), ACL, pp 460\u2013470"},{"key":"1383_CR12","doi-asserted-by":"crossref","unstructured":"Eisenstein J, Barzilay R (2008) Bayesian unsupervised topic segmentation. In: Proceedings of the conference on empirical methods on natural language processing (EMNLP), ACL, pp 334\u2013343","DOI":"10.3115\/1613715.1613760"},{"key":"1383_CR13","unstructured":"Feng W, Liu ZQ (2006) Self-validated and spatially coherent clustering with net-structured mrf and graph cuts. In: Proceedings of the international conference on pattern recognitition, vol 4, pp 37\u201340"},{"issue":"10","key":"1383_CR14","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1109\/TPAMI.2010.24","volume":"32","author":"W Feng","year":"2010","unstructured":"Feng W, Jia J, Liu ZQ (2010) Self-validated labeling of markov random fields for image segmentation. IEEE Trans Pattern Anal Mach Intell 32(10):1871\u20131887","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"1383_CR15","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1023\/B:JIIS.0000039534.65423.00","volume":"23","author":"P Fragkou","year":"2004","unstructured":"Fragkou P, Petridis V, Kehagias A (2004) A dynamic programming algorithm for linear text segmentation. J Intell Inform Syst 23(2):179\u2013197","journal-title":"J Intell Inform Syst"},{"key":"1383_CR16","doi-asserted-by":"crossref","unstructured":"Harwath DF, Hazen TJ, Glass JR (2013) Zero resource spoken audio corpus analysis. In: Proceedings of the international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 8555\u20138559","DOI":"10.1109\/ICASSP.2013.6639335"},{"key":"1383_CR17","doi-asserted-by":"crossref","unstructured":"Hazen TJ, Shen W, White C (2009) Query-by-example spoken term detection using phonetic posteriorgram templates. In: Proceedings of the Workshop Automatic speech recognition and understanding Workshop (ASRU), IEEE, pp 421\u2013426","DOI":"10.1109\/ASRU.2009.5372889"},{"issue":"1","key":"1383_CR18","first-page":"33","volume":"23","author":"M Hearst","year":"1997","unstructured":"Hearst M (1997) TextTiling: segmenting text into multi-paragraph subtopic passages. Comput Linguist 23(1):33\u201364","journal-title":"Comput Linguist"},{"key":"1383_CR19","doi-asserted-by":"crossref","unstructured":"Heinonen O (1998) Optimal multi-paragraph text segmentation by dynamic programming. In: Proceedings of the 36th annual meeting of the association for computational linguistics and 17th international conference on computational linguistics (COLING-ACL), Morgan Kaufmann Publishers\/ACL, pp 1484\u20131486","DOI":"10.3115\/980691.980814"},{"key":"1383_CR20","doi-asserted-by":"crossref","unstructured":"Hsu W, Chang SF, Huang CW, Kennedy L, Lin CY, Iyengar G (2003) Discovery and fusion of salient multimodal features toward news story segmentation. In: Electronic Imaging 2004, International Society for Optics and Photonics, pp 244\u2013258","DOI":"10.1117\/12.533037"},{"key":"1383_CR21","doi-asserted-by":"crossref","unstructured":"Huijbregts M, McLaren M, van Leeuwen D (2011) Unsupervised acoustic sub-word unit detection for query-by-example spoken term detection. In: Proceedings of the international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 4436\u20134439","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"1383_CR22","doi-asserted-by":"crossref","unstructured":"Jansen A, Church K (2011) Towards unsupervised training of speaker independent acoustic models. In: Proceedings of the annual conference of the international speech communication association (INTERSPEECH), ISCA, pp 1693\u20131692","DOI":"10.21437\/Interspeech.2011-184"},{"key":"1383_CR23","doi-asserted-by":"crossref","unstructured":"Jansen A, Thomas S, Hermansky H (2012) Intrinsic spectral analysis for zero and high resource speech recognition. In: Proceedings of the annual conference on international speech communication association (INTERSPEECH), ISCA, pp 878\u2013881","DOI":"10.21437\/Interspeech.2012-266"},{"key":"1383_CR24","doi-asserted-by":"crossref","unstructured":"Kintzley K, Jansen A, Church K, Hermansky H (2012) Inverting the point process model for fast phonetic keyword search. In: Proceedings of the annual conference of the international speech communication association (INTERSPEECH), ISCA, pp 2437\u20132440","DOI":"10.21437\/Interspeech.2012-638"},{"key":"1383_CR25","doi-asserted-by":"crossref","unstructured":"Kozima H (1993) Text segmentation based on similarity between words. In: Proceedings of the 31st annual meeting on Association for computational linguistics, pp 286\u2013288","DOI":"10.3115\/981574.981616"},{"issue":"5","key":"1383_CR26","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MSP.2005.1511823","volume":"22","author":"LS Lee","year":"2005","unstructured":"Lee LS, Chen B (2005) Spoken document understanding and organization. IEEE Signal Process Mag 22(5):42\u201360","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"1383_CR27","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1016\/S0022-0000(02)00010-7","volume":"65","author":"YL Lin","year":"2002","unstructured":"Lin YL, Jiang T, Chao KM (2002) Efficient algorithms for locating the length-constrained heaviest segments with applications to biomolecular sequence analysis. J Comput Syst Sci 65(3):570\u2013586","journal-title":"J Comput Syst Sci"},{"key":"1383_CR28","doi-asserted-by":"crossref","unstructured":"Liu Z, Xie L, Feng W (2010) Maximum lexical cohesion for fine-grained news story segmentation. In: Proceedings of the annual conference on international speech communication association (INTERSPEECH), ISCA, pp 1301\u20131304","DOI":"10.21437\/Interspeech.2010-407"},{"key":"1383_CR29","doi-asserted-by":"crossref","unstructured":"Lu M, Leung CC, Xie L, Ma B, Li H (2011) Probabilistic latent semantic analysis for broadcast news story segmentation. In: Proceedings of the annual conference of the international speech communication association (INTERSPEECH), ISCA, pp 1109\u20131112","DOI":"10.21437\/Interspeech.2011-376"},{"key":"1383_CR30","doi-asserted-by":"crossref","unstructured":"Lu X, Leung CC, Xie L, Ma B, Li H (2013) Broadcast news story segmentation using latent topics on data manifold. In: Proceedings of the international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 8465\u20138469","DOI":"10.1109\/ICASSP.2013.6639317"},{"key":"1383_CR31","doi-asserted-by":"crossref","unstructured":"Malioutov I, Barzilay R (2006) Minimum cut model for spoken lecture segmentation. Proceedings of the annual meeting on association for computational linguistics, ACL, pp 25\u201332","DOI":"10.3115\/1220175.1220179"},{"key":"1383_CR32","unstructured":"Malioutov I, Park A, Barzilay R, Glass J (2007) Making sense of sound: Unsupervised topic segmentation over acoustic input. In: Proceedings of the annual meeting on association for computational linguistics, ACL, vol 45, p 504"},{"issue":"5","key":"1383_CR33","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1080\/00107510500052444","volume":"46","author":"ME Newman","year":"2005","unstructured":"Newman ME (2005) Power laws, pareto distributions and zipf\u2019s law. Contemp Phys 46(5):323\u2013351","journal-title":"Contemp Phys"},{"issue":"1","key":"1383_CR34","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1109\/TASL.2007.909282","volume":"16","author":"AS Park","year":"2008","unstructured":"Park AS, Glass JR (2008) Unsupervised pattern discovery in speech. IEEE Trans Audio Speech Language Process 16(1):186\u2013197","journal-title":"IEEE Trans Audio Speech Language Process"},{"issue":"6","key":"1383_CR35","first-page":"903","volume":"53","author":"LX Peng Yang","year":"2013","unstructured":"Peng Yang LX, Chen H (2013) Speech pattern discovery using segmental dynamic time warping and posteriorgram features. J Tsinghua University (Sci and Technol) 53(6):903\u2013907","journal-title":"J Tsinghua University (Sci and Technol)"},{"key":"1383_CR36","unstructured":"Petr Sch AVP (2008) Phoneme recognition based on long temporal context. PhD thesis, Brno University of Technology, Faculty of Information Technology"},{"key":"1383_CR37","unstructured":"Ponte JM, Croft WB (1997) Text segmentation by topic. In: Proceedings of the 1st European conference on research and advanced technology for digital libraries, Springer, vol 1324, pp 113\u2013125"},{"key":"1383_CR38","doi-asserted-by":"crossref","unstructured":"Reynar JC (1994) An automatic method of finding topic boundaries. Proceedings of the annual meeting of the association for computational linguistics, ACL, pp 331\u2013333","DOI":"10.3115\/981732.981783"},{"key":"1383_CR39","unstructured":"Rosenberg A, Hirschberg J (2006) Story segmentation of broadcast news in English, Mandarin and Arabic. In: Proceedings of the human language technology conference of the North American chapter of the association for computational linguistics (HLT-NAACL), ACL, pp 125\u2013128"},{"issue":"8","key":"1383_CR40","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22(8):888\u2013905","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1383_CR41","first-page":"3","volume":"17","author":"N Stokes","year":"2004","unstructured":"Stokes N, Carthy J, Smeaton A (2004) SeLeCT: a lexical cohesion based news story segmentation system. J AI Commun 17(1):3\u201312","journal-title":"J AI Commun"},{"key":"1383_CR42","unstructured":"TDT2 (1998) The topic detection and tracking phase 2 (tdt2) evaluation plan. http:\/\/projects.ldc.upenn.edu\/TDT2"},{"key":"1383_CR43","doi-asserted-by":"crossref","unstructured":"Ten Bosch L, Cranen B (2007) A computational model for unsupervised word discovery. In: Proceedings of the annual conference of the international speech communication association (INTERSPEECH), ISCA, pp 1481\u20131484","DOI":"10.21437\/Interspeech.2007-429"},{"issue":"1","key":"1383_CR44","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1162\/089120101300346796","volume":"27","author":"G T\u00fcr","year":"2001","unstructured":"T\u00fcr G, Hakkani-T\u00fcr D, Stolcke A, Shriberg E (2001) Integrating prosodic and lexical cues for automatic topic segmentation. Comput linguist 27(1):31\u201357","journal-title":"Comput linguist"},{"key":"1383_CR45","doi-asserted-by":"crossref","unstructured":"Utiyama M, Isahara H (2001) A statistical model for domain-independent text segmentation. In: Proceedings of the 39th annual meeting of the association for computational linguistics, ACL, pp 499\u2013506","DOI":"10.3115\/1073012.1073076"},{"key":"1383_CR46","doi-asserted-by":"crossref","unstructured":"Wang H, Leung CC, Lee T, Ma B, Li H (2012a) An acoustic segment modeling approach to query-by-example spoken term detection. In: Proceedings of the international conference on acoustics, speech and signal processing. (ICASSP), IEEE, pp 5157\u20135160","DOI":"10.1109\/ICASSP.2012.6289081"},{"key":"1383_CR47","doi-asserted-by":"crossref","unstructured":"Wang X, Xie L, Ma B, Chng ES, Li H (2012b) Broadcast news story segmentation using conditional random fields and multi-modal features. IEICE Trans Inform Syst E95-D:1206\u20131215","DOI":"10.1587\/transinf.E95.D.1206"},{"key":"1383_CR48","doi-asserted-by":"crossref","unstructured":"Wang H, Lee T, Leung CC, Ma B, Li H (2013) Unsupervised mining of acoustic subword units with segment-level gaussian posteriorgrams. In: Proceedings of the annual conference of the international speech communication association (INTERSPEECH), ISCA, pp 2297\u20132301","DOI":"10.21437\/Interspeech.2013-538"},{"key":"1383_CR49","unstructured":"Wang X, Xie L, Ma B, Chng ES, Li H (2010) Modeling broadcast news prosody using conditional random fields for story segmentation. In: Proceedings of the Asia-Pacific signal and information processing association annual summit conference (APSIPA ASC), APSIPA, pp 253\u2013256"},{"key":"1383_CR50","doi-asserted-by":"crossref","unstructured":"Xie L, Liu C, Meng H (2007) Combined use of speaker-and tone-normalized pitch reset with pause duration for automatic story segmentation in mandarin broadcast news. In: Proceedings of the human language technologies: the conference of the North American chapter of the association for computational linguistics (HLT-NAACL), ACL, pp 193\u2013196","DOI":"10.3115\/1614108.1614157"},{"key":"1383_CR51","doi-asserted-by":"crossref","first-page":"2873","DOI":"10.1016\/j.ins.2011.02.013","volume":"181","author":"L Xie","year":"2011","unstructured":"Xie L, Yang Y, Liu ZQ (2011) On the effectiveness of subwords for lexical cohesion based story segmentation of Chinese broadcast news. Inform Sci 181:2873\u20132891","journal-title":"Inform Sci"},{"issue":"1","key":"1383_CR52","first-page":"264","volume":"20","author":"L Xie","year":"2012","unstructured":"Xie L, Zheng L, Liu Z, Zhang Y (2012) Laplacian eigenmaps for automatic story segmentation of broadcast news. IEEE Trans Audio Speech Language Process 20(1):264\u2013277","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"1383_CR53","doi-asserted-by":"crossref","unstructured":"Yamron J, carp I, Gillick L, Mulbregt P (1998) A hidden markov model approach to text segmentation and event tracking. In: Proceedings of the international conference on acoustics, speech and signal process. (ICASSP), IEEE, pp 333\u2013336","DOI":"10.1109\/ICASSP.1998.674435"},{"key":"1383_CR54","doi-asserted-by":"crossref","unstructured":"Zhang J, Xie L, Feng W, Zhang Y (2009) A subword normalized cut approach to automatic story segmentation of chinese broadcast news. Inform Retrieval Technol. Springer, pp 136\u2013148","DOI":"10.1007\/978-3-642-04769-5_12"},{"key":"1383_CR55","doi-asserted-by":"crossref","unstructured":"Zhang Y, Glass JR (2009) Unsupervised spoken keyword spotting via segmental dtw on gaussian posteriorgrams. In: Proceedings of the workshop on automatic Speech Recognitition and understanding (ASRU), IEEE, pp 398\u2013403","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"1383_CR56","doi-asserted-by":"crossref","unstructured":"Zhang Y, Glass JR (2010) Towards multi-speaker unsupervised speech pattern discovery. In: Proceedings of the international conference on acoustics, speech, and signal processing (ICASSP), IEEE, pp 4366\u20134369","DOI":"10.1109\/ICASSP.2010.5495637"},{"key":"1383_CR57","doi-asserted-by":"crossref","unstructured":"Zhang Y, Salakhutdinov R, Chang HA, Glass J (2012) Resource configurable spoken query detection using deep boltzmann machines. In: Proceedings of the international conference on acoustics, speech, and signal processing (ICASSP), IEEE, pp 5161\u20135164","DOI":"10.1109\/ICASSP.2012.6289082"},{"key":"1383_CR58","doi-asserted-by":"crossref","unstructured":"Zheng L, Leung CC, Xie L, Ma B, Li H (2012) Acoustic texttiling for story segmentation of spoken documents. In: Proceedings of the international conference on acoustics, speech, and signal processing (ICASSP), IEEE, pp 5121\u20135124","DOI":"10.1109\/ICASSP.2012.6289073"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-014-1383-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-014-1383-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-014-1383-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,12]],"date-time":"2022-04-12T07:33:59Z","timestamp":1649748839000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-014-1383-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,25]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,1]]}},"alternative-id":["1383"],"URL":"https:\/\/doi.org\/10.1007\/s00500-014-1383-9","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,25]]}}}