{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T02:34:43Z","timestamp":1781663683871,"version":"3.54.5"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"23","license":[{"start":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T00:00:00Z","timestamp":1565654400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T00:00:00Z","timestamp":1565654400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s11042-019-07991-6","type":"journal-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T05:02:52Z","timestamp":1565672572000},"page":"33999-34025","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Acoustic event diarization in TV\/movie audios using deep embedding and integer linear programming"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4362-1125","authenticated-orcid":false,"given":"Yanxiong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianku","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingle","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wucheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,8,13]]},"reference":[{"issue":"6","key":"7991_CR1","first-page":"1266","volume":"25","author":"E Benetos","year":"2017","unstructured":"Benetos E, Lafay G, Lagrange M, Plumbley MD (2017) Polyphonic sound event tracking using linear dynamical systems. IEEE\/ACM Trans on ASLP 25(6):1266\u20131277 IEEE\/ACM","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"7991_CR2","doi-asserted-by":"crossref","unstructured":"Burileanu D, Pascalin L, Burileanu C, Puchiu M (2000) An adaptive and fast speech detection algorithm. In: Proc. of Int\u2019l Workshop on Text, Speech and Dialogue, pp 177-182. Springer","DOI":"10.1007\/3-540-45323-7_30"},{"key":"7991_CR3","unstructured":"Diarization Error Rate, NIST. https:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt\/2006-spring\/code\/md-eval-v21.pl . Accessed 27 March 2016"},{"issue":"8","key":"7991_CR4","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861\u2013874 Elsevier","journal-title":"Pattern Recogn Lett"},{"key":"7991_CR5","doi-asserted-by":"crossref","unstructured":"Garcia-Romero D, Espy-Wilson CY (2010) Automatic acquisition device identification from speech recordings. In: Proc. ICASSP, pp 1806-1809. IEEE","DOI":"10.1109\/ICASSP.2010.5495407"},{"key":"7991_CR6","unstructured":"Gencoglu O, Virtanen T, Huttunen H (2014) Recognition of acoustic events using deep neural network. In: Proc. of European Conf. on Signal Process., pp 506-510. ISCA"},{"issue":"8","key":"7991_CR7","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"GE Hinton","year":"2002","unstructured":"Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771\u20131800 MIT Press","journal-title":"Neural Comput"},{"key":"7991_CR8","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504\u2013507 AAAS","journal-title":"Science"},{"key":"7991_CR9","doi-asserted-by":"crossref","unstructured":"K\u00fc\u00e7\u00fckbay SE, Sert M (2015) Audio-based event detection in office live environments using optimized MFCC-SVM approach. In: Proc. of IEEE International Conference on Semantic Computing, pp 475-480. IEEE","DOI":"10.1109\/ICOSC.2015.7050855"},{"key":"7991_CR10","doi-asserted-by":"crossref","unstructured":"Kumar A, Dighe P, Singh R, Chaudhuri S, Raj B (2012) Audio event detection from acoustic unit occurrence patterns. In: Proc. of IEEE ICASSP, pp 489-492. IEEE","DOI":"10.1109\/ICASSP.2012.6287923"},{"key":"7991_CR11","doi-asserted-by":"crossref","unstructured":"Laffitte P, Sodoyer D, Tatkeu C, Girin L (2016) Deep neural networks for automatic detection of screams and shouted speech in subway trains. In: Proc. of IEEE ICASSP, pp 6460-6464. IEEE","DOI":"10.1109\/ICASSP.2016.7472921"},{"key":"7991_CR12","unstructured":"Lee D, Lee S, Han Y, Lee K (2017) Ensemble of convolutional neural networks for weakly-supervised sound event detection using multiple scale input. In: Proc. DCASE2017 Workshop, pp 74-79. Tampere University of Technology"},{"issue":"8","key":"7991_CR13","doi-asserted-by":"publisher","first-page":"1625","DOI":"10.1016\/j.sigpro.2009.03.001","volume":"89","author":"YX Li","year":"2009","unstructured":"Li YX, He Q, Kwong S, Li T, Yang J (2009) Characteristics-based effective applause detection for meeting speech. Signal Process 89(8):1625\u20131633 Elsevier","journal-title":"Signal Process"},{"issue":"8","key":"7991_CR14","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1049\/iet-spr.2013.0340","volume":"8","author":"Y Li","year":"2014","unstructured":"Li Y, Jin H, Li W, He Q, Zhu Z, Feng X (2014) Fast speaker clustering using distance of feature matrix mean and adaptive convergence threshold. IET Signal Process 8(8):844\u2013851 IET","journal-title":"IET Signal Process"},{"key":"7991_CR15","doi-asserted-by":"publisher","first-page":"58043","DOI":"10.1109\/ACCESS.2018.2872931","volume":"6","author":"Y Li","year":"2018","unstructured":"Li Y, Li X, Zhang Y, Liu M, Wang W (2018) Anomalous sound detection using deep audio representation and a BLSTM network for audio surveillance of roads. IEEE Access 6:58043\u201358055 IEEE","journal-title":"IEEE Access"},{"key":"7991_CR16","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.dsp.2016.12.012","volume":"63","author":"Y Li","year":"2017","unstructured":"Li Y, Wang Q, Li X, Zhang X, Zhang Y, Chen A, He Q, Huang Q (2017) Unsupervised detection of acoustic events using information bottleneck principle. Digital Signal Process 63:123\u2013134 Elsevier","journal-title":"Digital Signal Process"},{"key":"7991_CR17","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.csl.2016.09.002","volume":"42","author":"Y Li","year":"2017","unstructured":"Li Y, Wang Q, Zhang X, Li W, Li X, Yang J, Feng X, Huang Q, He Q (2017) Unsupervised classification of speaker roles in multi-participant conversational speech. Comput Speech Lang 42:81\u201399 Elsevier","journal-title":"Comput Speech Lang"},{"key":"7991_CR18","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1007\/s11042-016-4332-z","volume":"77","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang X, Jin H, Li X, Wang Q, He Q, Huang Q (2018) Using multi-stream hierarchical deep neural network to extract deep audio feature for acoustic events detection. Multimed Tools Appl 77:897\u2013916 Springer","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"7991_CR19","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/TMM.2007.911304","volume":"10","author":"L Lu","year":"2008","unstructured":"Lu L, Alan H (2008) Audio keywords discovery for text-like audio content analysis and retrieval. IEEE Trans on Multimedia 10(1):74\u201385 IEEE","journal-title":"IEEE Trans on Multimedia"},{"key":"7991_CR20","doi-asserted-by":"crossref","unstructured":"Lu L, Ge F, Zhao Q, Yan Y (2010) A SVM-based audio event detection system. In: Proc. of Int\u2019l Conf. on Electrical and Control Engineering, pp 292-295. IEEE","DOI":"10.1109\/iCECE.2010.78"},{"key":"7991_CR21","doi-asserted-by":"crossref","unstructured":"Lu X, Tsao Y, Matsuda S, Hori C (2014) Sparse representation based on a bag of spectral exemplars for acoustic event detection. In: Proc. of IEEE ICASSP, pp 6255-6259. IEEE","DOI":"10.1109\/ICASSP.2014.6854807"},{"issue":"3","key":"7991_CR22","first-page":"540","volume":"23","author":"I McLoughlin","year":"2015","unstructured":"McLoughlin I, Zhang H, Xie Z, Song Y, Xiao W (2015) Robust sound event classification using deep neural networks. IEEE\/ACM Trans on ASLP 23(3):540\u2013552 IEEE","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"7991_CR23","unstructured":"Mesaros A, Heittola T, Diment A, Elizalde B, Shah A, Vincent E, Raj B, Virtanen T (2017) DCASE 2017 challenge setup: tasks, datasets and baseline system, in Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop. Tampere University of Technology"},{"issue":"2","key":"7991_CR24","first-page":"356","volume":"20","author":"XA Miro","year":"2012","unstructured":"Miro XA, Bozonnet S, Evans N, Fredouille C, Friedland G, Vinyals O (2012) Speaker diarization: a review of recent research. IEEE Trans ASLP 20(2):356\u2013370 IEEE","journal-title":"IEEE Trans ASLP"},{"key":"7991_CR25","doi-asserted-by":"crossref","unstructured":"Niessen ME, Kasteren TLMV, Merentitis A (2013) Hierarchical modeling using automated sub-clustering for sound event recognition. In: Proc. of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp 1-4. IEEE","DOI":"10.1109\/WASPAA.2013.6701862"},{"issue":"1","key":"7991_CR26","first-page":"20","volume":"23","author":"H Phan","year":"2015","unstructured":"Phan H, Maa\u00df M, Mazur R, Mertins A (2015) Random regression forests for acoustic event detection and classification. IEEE\/ACM Trans on ASLP 23(1):20\u201331 IEEE\/ACM","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"7991_CR27","unstructured":"Plumbley MD, Kroos C, Bello JP, Richard G, Ellis DPW, Mesaros A (2018) Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018), 2018. Surrey University"},{"key":"7991_CR28","doi-asserted-by":"crossref","unstructured":"Portelo J, Bugalho M, Trancoso I, Neto J, Abad A, Serralheiro A (2009) Non-speech audio event detection. In: Proc. of IEEE ICASSP, pp 1973-1976. IEEE","DOI":"10.1109\/ICASSP.2009.4959998"},{"issue":"1","key":"7991_CR29","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted Gaussian mixture models. Digit Signal Process 10(1):19\u201341 Elsevier","journal-title":"Digit Signal Process"},{"key":"7991_CR30","unstructured":"Reynolds DA, Torres-Carrasquillo P (2005) Approaches and applications of audio diarization. In: Proc. of IEEE ICASSP, pp 953-956. IEEE"},{"issue":"5","key":"7991_CR31","doi-asserted-by":"publisher","first-page":"4134","DOI":"10.1121\/1.3699200","volume":"131","author":"MR Sch\u00e4dler","year":"2012","unstructured":"Sch\u00e4dler MR, Meyer BT, Kollmeier B (2012) Spectro-temporal modulation subspace-spanning filter bank features for robust automatic speech recognition. J Acoust Soc Amer 131(5):4134\u20134151 Acoustical Society of America","journal-title":"J Acoust Soc Amer"},{"issue":"12","key":"7991_CR32","first-page":"2198","volume":"23","author":"J Schr\u00f6der","year":"2015","unstructured":"Schr\u00f6der J, Goetze S, Anem\u00fcller J (2015) Spectro-temporal Gabor filterbank features for acoustic event detection. IEEE\/ACM Trans on ASLP 23(12):2198\u20132208 IEEE\/ACM","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"7991_CR33","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der J, Goetze S, Gr\u00fctzmacher V, Anem\u00fcller J (2013) Automatic acoustic siren detection in traffic noise by part-based models. In: Proc. of IEEE ICASSP, pp 493-497. IEEE","DOI":"10.1109\/ICASSP.2013.6637696"},{"issue":"6","key":"7991_CR34","first-page":"1304","volume":"25","author":"J Schr\u00f6der","year":"2017","unstructured":"Schr\u00f6der J, Moritz N, Anem\u00fcller J, Goetze S, Kollmeier B (2017) Classifier architectures for acoustic scenes and events: implications for DNNs, TDNNs, and perceptual features from DCASE 2016. IEEE\/ACM Trans on ASLP 25(6):1304\u20131314 IEEE\/ACM","journal-title":"IEEE\/ACM Trans on ASLP"},{"key":"7991_CR35","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der J, Moritz N, Sch\u00e4dler MR, Cauchi B, Adiloglu K, Anem\u00fcller J, Doclo S, Kollmeier B, Goetze S (2013) On the use of spectro-temporal features for the IEEE AASP challenge detection and classification of acoustic scenes and events. In: Proc. oF IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp1-4. IEEE","DOI":"10.1109\/WASPAA.2013.6701868"},{"issue":"10","key":"7991_CR36","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"17","author":"D Stowell","year":"2015","unstructured":"Stowell D, Giannoulis D, Benetos E, Lagrange M, Plumbley MD (2015) Detection and classification of acoustic scenes and events. IEEE Trans on Multimedia 17(10):1733\u20131746 IEEE","journal-title":"IEEE Trans on Multimedia"},{"key":"7991_CR37","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-540-69568-4_29","volume":"4122","author":"A Temko","year":"2007","unstructured":"Temko A, Malkin R, Zieger C, Macho D, Nadeu C, Omologo M (2007) CLEAR evaluation of acoustic event detection and classification systems. Lect Notes Comput Sci 4122:311\u2013322 Springer","journal-title":"Lect Notes Comput Sci"},{"issue":"6","key":"7991_CR38","first-page":"1556","volume":"19","author":"HD Tran","year":"2011","unstructured":"Tran HD, Li H (2011) Sound event recognition with probabilistic distance SVMs. IEEE Trans on ASLP 19(6):1556\u20131568 IEEE","journal-title":"IEEE Trans on ASLP"},{"key":"7991_CR39","doi-asserted-by":"crossref","unstructured":"Valente F, Motlicek P, Vijayasenan D (2010) Variational Bayesian speaker diarization of meeting recordings. In: Proc. of IEEE ICASSP, pp 4954-4957. IEEE","DOI":"10.1109\/ICASSP.2010.5495087"},{"key":"7991_CR40","unstructured":"Virtanen T, Mesaros A, Heittola T, Plumbley MD, Foster P, Benetos E, Lagrange M (2016) Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016), 2016. Tampere Univeristy of Technology"},{"key":"7991_CR41","doi-asserted-by":"crossref","unstructured":"Wang Y, Dawat S, Metze F (2014) Exploring audio semantic concepts for event-based video retrieval. In: Proc. of IEEE ICASSP, pp 1360-1364. IEEE","DOI":"10.1109\/ICASSP.2014.6853819"},{"key":"7991_CR42","doi-asserted-by":"crossref","unstructured":"Xu Y , Kong Q, Wang W, Plumbley MD (2018) Large-scale weakly supervised audio classification using gated convolutional neural network. In: Proc. IEEE ICASSP, pp 121-125. IEEE","DOI":"10.1109\/ICASSP.2018.8461975"},{"issue":"3","key":"7991_CR43","doi-asserted-by":"publisher","first-page":"638","DOI":"10.4304\/jcp.8.3.638-644","volume":"8","author":"J Yang","year":"2013","unstructured":"Yang J, He Q, Li Y, Zhang X (2013) Speaker change detection based on mean shift. J Comput 8(3):638\u2013644 Hindawi","journal-title":"J Comput"},{"key":"7991_CR44","doi-asserted-by":"crossref","unstructured":"Yu D, Seltzer ML (2011) Improved bottleneck features using pre-trained deep neural networks. In: Proc. of INTERSPEECH, pp 237-240. ISCA","DOI":"10.21437\/Interspeech.2011-91"},{"key":"7991_CR45","doi-asserted-by":"crossref","unstructured":"Zhang X, He Q, Feng X (2015) Acoustic feature extraction by tensor-based sparse representation for sound effects classification. In: Proc. of IEEE ICASSP, pp 166-170. IEEE","DOI":"10.1109\/ICASSP.2015.7177953"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07991-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-07991-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07991-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T14:20:39Z","timestamp":1664115639000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-07991-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,13]]},"references-count":45,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["7991"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-07991-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,13]]},"assertion":[{"value":"7 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}