{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T09:24:17Z","timestamp":1759742657273},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2015,3,25]],"date-time":"2015-03-25T00:00:00Z","timestamp":1427241600000},"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":[[2016,6]]},"DOI":"10.1007\/s11042-015-2555-z","type":"journal-article","created":{"date-parts":[[2015,3,24]],"date-time":"2015-03-24T06:28:37Z","timestamp":1427178517000},"page":"6071-6089","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Robust scream sound detection via sound event partitioning"],"prefix":"10.1007","volume":"75","author":[{"given":"Baiying","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,3,25]]},"reference":[{"key":"2555_CR1","unstructured":"addnoise. http:\/\/www.mathworks.com\/matlabcentral\/fileexchange\/32136-add-noise\/content\/addnoise\/addnoise.m"},{"key":"2555_CR2","doi-asserted-by":"crossref","unstructured":"Ali S, Smith-Miles KA (2006) Improved support vector machine generalization using normalized input space. In: Proc. of 19th Australian Joint Conference on Artificial Intelligence. pp 362\u2013371","DOI":"10.1007\/11941439_40"},{"key":"2555_CR3","doi-asserted-by":"crossref","unstructured":"Atrey PK, Maddage NC, Kankanhalli MS (2006) Audio based event detection for multimedia surveillance. In: Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing. pp V813-V816","DOI":"10.1109\/ICASSP.2006.1661400"},{"issue":"6","key":"2555_CR4","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TASL.2009.2017438","volume":"17","author":"S Chu","year":"2009","unstructured":"Chu S, Narayanan S, Kuo CCJ (2009) Environmental sound recognition with time-frequency audio features. IEEE Trans Audio, Speech Lang Process 17(6):1142\u20131158","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"key":"2555_CR5","doi-asserted-by":"crossref","unstructured":"Clavel C, Ehrette T, Richard G (2005) Events detection for an audio-based surveillance system. In: Proc.of IEEE International Conference on Multimedia and Expo. pp 1306\u20131309","DOI":"10.1109\/ICME.2005.1521669"},{"issue":"4","key":"2555_CR6","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process 28(4):357\u2013366","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"2","key":"2555_CR7","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/TASL.2012.2226160","volume":"21","author":"J Dennis","year":"2013","unstructured":"Dennis J, Tran HD, Chng E-S (2013) Image feature representation of the subband power distribution for robust sound event classification. IEEE Trans Audio, Speech Lang Process 21(2):367\u2013377","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"issue":"9","key":"2555_CR8","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1016\/j.patrec.2013.02.015","volume":"34","author":"J Dennis","year":"2013","unstructured":"Dennis J, Tran HD, Chng ES (2013) Overlapping sound event recognition using local spectrogram features and the generalised hough transform. Pattern Recogn Lett 34(9):1085\u20131093","journal-title":"Pattern Recogn Lett"},{"issue":"2","key":"2555_CR9","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/LSP.2010.2100380","volume":"18","author":"J Dennis","year":"2011","unstructured":"Dennis J, Tran HD, Li H (2011) Spectrogram image feature for sound event classification in mismatched conditions. IEEE Signal Process Lett 18(2):130\u2013133","journal-title":"IEEE Signal Process Lett"},{"key":"2555_CR10","unstructured":"Ferrer L, Bratt H, Burget L, Cernocky H, Glembek O, Graciarena M, Lawson A, Lei Y, Matejka P, Plchot O (2011) Promoting robustness for speaker modeling in the community: the PRISM evaluation set. In: Proc.of NIST 2011 Workshop"},{"issue":"7","key":"2555_CR11","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1109\/TASL.2011.2118753","volume":"19","author":"B Ghoraani","year":"2011","unstructured":"Ghoraani B, Krishnan S (2011) Time-frequency matrix feature extraction and classification of environmental audio signals. IEEE Trans Audio, Speech Lang Process 19(7):2197\u20132209","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"issue":"1","key":"2555_CR12","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TNN.2002.806626","volume":"14","author":"G Guo","year":"2003","unstructured":"Guo G, Li SZ (2003) Content-based audio classification and retrieval by support vector machines. IEEE Trans Neural Netw 14(1):209\u2013215","journal-title":"IEEE Trans Neural Netw"},{"issue":"8","key":"2555_CR13","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.1109\/TASL.2013.2256895","volume":"21","author":"V Hautamaki","year":"2013","unstructured":"Hautamaki V, Kinnunen T, Sedlak F, Lee KA, Ma B, Li H (2013) Sparse classifier fusion for speaker verification. IEEE Trans Audio, Speech Lang Process 21(8):1622\u20131631","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"key":"2555_CR14","unstructured":"Huang W, Chiew T-K, Li H, Kok TS, Biswas J (2010) Scream detection for home applications. In: Proc.of 6th IEEE Conference on Industrial Electronics and Applications. pp 2115\u20132120"},{"key":"2555_CR15","unstructured":"Human Sound Effects. http:\/\/www.sound-ideas.com\/"},{"key":"2555_CR16","doi-asserted-by":"crossref","unstructured":"J\u00e9gou H, Chum O (2012) Negative evidences and co-occurences in image retrieval: the benefit of PCA and whitening. In: Proc.of European Conference on Computer Vision. pp 774\u2013787","DOI":"10.1007\/978-3-642-33709-3_55"},{"key":"2555_CR17","doi-asserted-by":"crossref","unstructured":"Kim MJ, Kim H (2011) Automatic extraction of pornographic contents using radon transform based audio features. In: Prof. of 9th International Workshop onContent-Based Multimedia Indexing. pp 205\u2013210","DOI":"10.1109\/CBMI.2011.5972546"},{"issue":"1","key":"2555_CR18","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen T, Li H (2010) An overview of text-independent speaker recognition: from features to supervectors. Speech Comm 52(1):12\u201340","journal-title":"Speech Comm"},{"issue":"1","key":"2555_CR19","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s11042-012-1183-0","volume":"68","author":"J Kotus","year":"2014","unstructured":"Kotus J, Lopatka K, Czyzewski A (2014) Detection and localization of selected acoustic events in acoustic field for smart surveillance applications. Multimedia Tools Appl 68(1):5\u201321","journal-title":"Multimedia Tools Appl"},{"key":"2555_CR20","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neucom.2014.04.002","volume":"141","author":"B Lei","year":"2014","unstructured":"Lei B, Rahman SA, Song I (2014) Content-based classification of breath sound with enhanced features. Neurocomputing 141:139\u2013147","journal-title":"Neurocomputing"},{"key":"2555_CR21","doi-asserted-by":"crossref","unstructured":"Liao W-H, Lin Y-K (2009) Classification of non-speech human sounds: Feature selection and snoring sound analysis. In: Proc. of IEEE International Conference on on Systems, Man and Cybernetics. pp 2695\u20132700","DOI":"10.1109\/ICSMC.2009.5346556"},{"key":"2555_CR22","doi-asserted-by":"crossref","unstructured":"Mak M-W, Kung S-Y (2012) Low-power SVM classifiers for sound event classification on mobile devices. In: Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing pp 1985\u20131988","DOI":"10.1109\/ICASSP.2012.6288296"},{"issue":"1","key":"2555_CR23","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.specom.2010.06.011","volume":"53","author":"M-W Mak","year":"2011","unstructured":"Mak M-W, Rao W (2011) Utterance partitioning with acoustic vector resampling for GMM\u2013SVM speaker verification. Speech Comm 53(1):119\u2013130","journal-title":"Speech Comm"},{"issue":"1","key":"2555_CR24","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.csl.2013.07.003","volume":"28","author":"M-W Mak","year":"2014","unstructured":"Mak M-W, Yu H-B (2014) A study of voice activity detection techniques for NIST speaker recognition evaluations. Comput Speech Lang 28(1):295\u2013313","journal-title":"Comput Speech Lang"},{"key":"2555_CR25","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H (2008) Introduction to information retrieval, vol 1. Cambridge University Press, Cambridge"},{"key":"2555_CR26","doi-asserted-by":"crossref","unstructured":"Martin A, Doddington G, Kamm T, Ordowski M, Przybocki M (1997) The DET curve in assessment of detection task performance. In: Proc.of 5th European Conference on Speech Communication and Technology. pp 1895\u20131898","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"2555_CR27","doi-asserted-by":"crossref","unstructured":"Ntalampiras S, Potamitis I, Fakotakis N (2009) On acoustic surveillance of hazardous situations. In: Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing. pp 165\u2013168","DOI":"10.1109\/ICASSP.2009.4959546"},{"key":"2555_CR28","unstructured":"Penet C, Demarty C-H, Gravier G, Gros P (2014) Variability modelling for audio events detection in movies. Multimedia Tools and Applications 1\u201331"},{"key":"2555_CR29","unstructured":"PRISM-SET. https:\/\/code.google.com\/p\/prism-set\/"},{"issue":"12","key":"2555_CR30","doi-asserted-by":"crossref","first-page":"3140","DOI":"10.1109\/TIT.2002.805090","volume":"48","author":"H Ralf","year":"2002","unstructured":"Ralf H, Thore G (2002) A PAC-Bayesian margin bound for linear classifiers. IEEE Trans Inf Theory 48(12):3140\u20133150","journal-title":"IEEE Trans Inf Theory"},{"issue":"5","key":"2555_CR31","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1109\/TASL.2013.2243436","volume":"21","author":"W Rao","year":"2013","unstructured":"Rao W, Mak M-W (2013) Boosting the performance of i-vector based speaker verification via utterance partitioning. IEEE Trans Audio, Speech Lang Process 21(5):1012\u20131022","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"key":"2555_CR32","unstructured":"rir. http:\/\/sgm-audio.com\/research\/rir\/rir.html"},{"issue":"3","key":"2555_CR33","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez J, Perronnin F, Mensink T, Verbeek J (2013) Image classification with the fisher vector: theory and practice. Int J Comput Vis 105(3):222\u2013245","journal-title":"Int J Comput Vis"},{"key":"2555_CR34","doi-asserted-by":"crossref","unstructured":"Simonyan K, Parkhi OM, Vedaldi A, Zisserman A (2013) Fisher Vector Faces in the Wild. In: Proc. of British Machine Vision Conference. pp 8.1-8.12","DOI":"10.5244\/C.27.8"},{"issue":"6","key":"2555_CR35","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1109\/TASL.2010.2093519","volume":"19","author":"HD Tran","year":"2011","unstructured":"Tran HD, Li H (2011) Sound event recognition with probabilistic distance SVMs. IEEE Trans Audio, Speech Lang Process 19(6):1556\u20131568","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"key":"2555_CR36","doi-asserted-by":"crossref","unstructured":"Valenzise G, Gerosa L, Tagliasacchi M, Antonacci F, Sarti A (2007) Scream and gunshot detection and localization for audio-surveillance systems. In: Proc.of IEEE Conference on Advanced Video and Signal Based Surveillance. pp 21\u201326","DOI":"10.1109\/AVSS.2007.4425280"},{"issue":"3","key":"2555_CR37","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga A, Steeneken HJM (1993) Assessment for automatic speech recognition: II. NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Comm 12(3):247\u2013251","journal-title":"Speech Comm"},{"issue":"2","key":"2555_CR38","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1109\/TASL.2012.2221459","volume":"21","author":"Y Wang","year":"2013","unstructured":"Wang Y, Han K, Wang D (2013) Exploring monaural features for classification-based speech segregation. IEEE Trans Audio, Speech Lang Process 21(2):270\u2013279","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"issue":"5","key":"2555_CR39","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1109\/TASL.2012.2186803","volume":"20","author":"X Zhao","year":"2012","unstructured":"Zhao X, Shao Y, Wang D (2012) CASA-based robust speaker identification. IEEE Trans Audio, Speech Lang Process 20(5):1608\u20131616","journal-title":"IEEE Trans Audio, Speech Lang Process"},{"key":"2555_CR40","doi-asserted-by":"crossref","unstructured":"Zhao X, Wang D (2013) Analyzing noise robustness of MFCC and GFCC features in speaker identification. In: Proc.of IEEE International Conference on Acoustics, Speech and Signal Processing. pp 7204\u20137208","DOI":"10.1109\/ICASSP.2013.6639061"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-015-2555-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-015-2555-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-015-2555-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T23:39:17Z","timestamp":1691537957000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-015-2555-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3,25]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["2555"],"URL":"https:\/\/doi.org\/10.1007\/s11042-015-2555-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3,25]]}}}