{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T01:55:20Z","timestamp":1790646920274,"version":"4.1.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1007\/s11042-014-2038-7","type":"journal-article","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T10:59:52Z","timestamp":1404125992000},"page":"1143-1173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Variability modelling for audio events detection in movies"],"prefix":"10.1007","volume":"74","author":[{"given":"C\u00e9dric","family":"Penet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire-H\u00e9l\u00e8ne","family":"Demarty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Gravier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Gros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,7,1]]},"reference":[{"issue":"1","key":"2038_CR1","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/29.1486","volume":"36","author":"R Andre-Obrecht","year":"1988","unstructured":"Andre-Obrecht R (1988) A new statistical approach for the automatic segmentation of continuous speech signals. IEEE trans Audio, Speech Sig Process 36(1):29\u201340","journal-title":"IEEE trans Audio, Speech Sig Process"},{"key":"2038_CR2","unstructured":"Atrey PK, Maddage NC, Kankanhalli MS (2006) Audio based event detection for multimedia surveillance. In: 31st IEEE international conference on acoustics, speech and signal processing. Toulouse, pp V\u2013V"},{"issue":"6","key":"2038_CR3","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1109\/LSP.2004.827951","volume":"11","author":"JP Bello","year":"2004","unstructured":"Bello JP, Duxbury C, Davies M, Sandler M (2004) On the Use of phase and energy for musical onset detection in the complex domain. Signal Proc Lett 11(6):553\u2013556","journal-title":"Signal Proc Lett"},{"key":"2038_CR4","unstructured":"Bonastre JF, Scheffer N, Matrouf D, Fredouille C, Larcher A, Preti A, Pouchoulin G, Evans N, Fauve B, Mason J (2008) ALIZE\/SpkDet: a state-of-the-art open source software for speaker Recognition. In: IEEE proceedings of odyssey: the speaker and language recognition workshop. Stellenbosch"},{"key":"2038_CR5","doi-asserted-by":"crossref","unstructured":"Burred JJ (2012) Genetic motif discovery applied to audio analysis. In: 37th international conference on acoustics, speech, and signal processing. Kyoto, pp 361\u2013364","DOI":"10.1109\/ICASSP.2012.6287891"},{"key":"2038_CR6","unstructured":"Chin ML , Burred JJ (2012) Audio event detection based on layered symbolic sequence representations. In: 37th international conference on acoustics, speech, and signal processing. Kyoto, pp 1953\u20131956"},{"key":"2038_CR7","unstructured":"Demarty C-H, Penet C, Gravier G, Soleymani M (2012) A benchmarking campaign for the multimodal detection of violent scenes in movies. In: ECCV 2012 workshop on information fusion in computer vision for concept recognition. Firenze, pp 416\u2013425"},{"key":"2038_CR8","unstructured":"Gravier G, Demarty C-H, Baghdadi S, Gros P (2012) Classification-oriented structure learning in Bayesian networks for multimodal event detection in videos. In: Multimedia sools and applications. pp 1\u201317"},{"key":"2038_CR9","doi-asserted-by":"crossref","unstructured":"Giannakopoulos T , Kosmopoulos DI, Aristidou A, Theodoridis S (2007) A multi-class audio classification method with respect to violent content in movies using Bayesian networks. In: IEEE workshop on multimedia signal processing. Crete, pp 90\u201393","DOI":"10.1109\/MMSP.2007.4412825"},{"key":"2038_CR10","doi-asserted-by":"crossref","unstructured":"Ionescu B, Schluter J, Mironica\u030c I, Schedl M (2013) A nave mid-level concept-based fusion approach to violence Detection in Hollywood Movies. In: ACM international conference on multimedia retrieval. Dallas Texas, pp 215\u2013222","DOI":"10.1145\/2461466.2461502"},{"issue":"1","key":"2038_CR11","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H J\u2019egou","year":"2011","unstructured":"J\u2019egou H, Douze M, Schmid C (2011) Product quantization for nearest neighbor search. IEEE Tran Pattern Anal Mach Intell 33(1):117\u2013128","journal-title":"IEEE Tran Pattern Anal Mach Intell"},{"key":"2038_CR12","doi-asserted-by":"crossref","unstructured":"Jin Q, Schulam PF, Rawat S, Burger S, Ding D, Metze F (2012) Event-based video retrieval using audio. In: INTERSPEECH. Portland","DOI":"10.21437\/Interspeech.2012-556"},{"issue":"1","key":"2038_CR13","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1109\/TASL.2008.2007613","volume":"17","author":"C Joder","year":"2009","unstructured":"Joder C, Essid S , Richard G (2009) Temporal integration for audio classification with application to musical instrument classification. IEEE Trans Audio, Speech, Lang Process 17(1):174\u2013186","journal-title":"IEEE Trans Audio, Speech, Lang Process"},{"key":"2038_CR14","unstructured":"Kenny P (2006) Joint factor analysis of speaker and session variability: theory and algorithms technical report, Centre de recherche en informatique de montreal (CRIM)"},{"key":"2038_CR15","doi-asserted-by":"crossref","unstructured":"Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley-Interscience","DOI":"10.1002\/0471660264"},{"key":"2038_CR16","unstructured":"Lucas P (2002) Restricted Bayesian network structure learning. In: Advances in Bayesian networks, studies in fuzziness and soft computing. pp 217\u2013232"},{"key":"2038_CR17","unstructured":"McKinney MF, Breebaart J (2003) Features for audio and music classification. In: Proceeding of the international society for music information retrieval. Washington, DC, pp 151\u2013158"},{"key":"2038_CR18","doi-asserted-by":"crossref","unstructured":"Matrouf D, Scheffer N, Fauve B, Bonastrem JF (2007) A straightforward and efficient implementation of the factor analysis model for speaker verification. In: INTERSPEECH. Antwerp, pp 1242\u20131245","DOI":"10.21437\/Interspeech.2007-156"},{"issue":"3","key":"2038_CR19","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.csl.2010.11.001","volume":"25","author":"D Matrouf","year":"2011","unstructured":"Matrouf D, Verdet F, Rouvier M, Bonastre JF, Linares G (2011) Modeling nuisance variabilities with factor analysis for GMM-based Audio Pattern Classification. Comput Speech & Lang 25(3):481\u2013498","journal-title":"Comput Speech & Lang"},{"key":"2038_CR20","unstructured":"Ono N, Miyamoto K, Kameoka H, Sagayama S (2008) A real-time equalizer of harmonic and percussive components in music signals. In: International symposium\/conference on music information Retrieval, Philadelphia. pp 139\u2013144"},{"key":"2038_CR21","doi-asserted-by":"crossref","unstructured":"Penet C, Demarty C-H, Gravier G, Gros P (2012) Multimodal information fusion and temporal integration for violence detection in movies. In: 37th international conference on acoustics, speech, and signal processing. Kyoto, pp 2393\u20132396","DOI":"10.1109\/ICASSP.2012.6288397"},{"key":"2038_CR22","doi-asserted-by":"crossref","unstructured":"Penet C, Demarty C-H, Gravier G, Gros P (2013) Audio event detection in movies using multiple audio words and contextual Bayesian networks. In 11th international workshop on content-based multimedia Indexing, pp 17\u201322, Veszprem, Hungary, June 2013","DOI":"10.1109\/CBMI.2013.6576546"},{"key":"2038_CR23","unstructured":"Ramona M, Richard G (2009) Comparison of different strategies for a SVM-Based audio segmentation. In: European conference on signal processing. Glasgow, pp 20\u201324"},{"key":"2038_CR24","doi-asserted-by":"crossref","unstructured":"Rouvier M, Matrouf D, Linars G (2009) Factor analysis for audio-based video genre classification. In: INTERSPEECH. Brighton","DOI":"10.21437\/Interspeech.2009-336"},{"key":"2038_CR25","doi-asserted-by":"crossref","unstructured":"Saunders J (1996) Real-time discrimination of broadcast speech\/music. In: IEEE international conference on acoustics, speech and signal processing, vol 2. Atlanta, pp 993\u2013996","DOI":"10.1109\/ICASSP.1996.543290"},{"key":"2038_CR26","doi-asserted-by":"crossref","unstructured":"Schluter J, Ionescu B, Mironica I, Schedl M (2012) ARF @ MediaEval 2012: an uninformed approach to violence detection in hollywood movies. In: MediaEval 2012 Workshop. ceur-ws.org","DOI":"10.1145\/2461466.2461502"},{"key":"2038_CR27","doi-asserted-by":"crossref","unstructured":"Trancoso I, Pellegrini T, Portelo J, Meinedo H, Bugalho M, Abad A, Neto J (2009) Audio contributions to semantic video search. In: International conference on multimedia and expo. New York, pp 630\u2013633","DOI":"10.1109\/ICME.2009.5202575"},{"key":"2038_CR28","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.csl.2007.05.003","volume":"22","author":"R Vogt","year":"2008","unstructured":"Vogt R, Sridha S (January 2008) Explicit modelling of session variability for speaker verification. Comput Speech Lang 22:17\u201338","journal-title":"Comput Speech Lang"},{"key":"2038_CR29","unstructured":"Valenzise G, Gerosa L, Tagliasacchi M, Antonacci F, Sarti A (2007) Scream and gunshot detection in noisy environments. In: EUSIPCO"},{"key":"2038_CR30","doi-asserted-by":"crossref","unstructured":"Vair C, Colibro D, Castaldo F, Dalmasso E, Laface P (2006) Channel factors compensation in model and feature domain for speaker recognition. In: IEEE proceedings of odyssey: the speaker and language recognition workshop. San Juan pp 1\u20136","DOI":"10.1109\/ODYSSEY.2006.248117"},{"key":"2038_CR31","doi-asserted-by":"crossref","unstructured":"Zhuang X, Tsakalidis S, Wu S, Natarajan P, Prasad R, Natarajan P (2012) Compact audio representation for event detection in consumer media. In: INTERSPEECH. Portland","DOI":"10.21437\/Interspeech.2012-557"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2038-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-2038-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-2038-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T19:15:44Z","timestamp":1689362144000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-2038-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,1]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,2]]}},"alternative-id":["2038"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-2038-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,1]]}}}