{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T02:01:39Z","timestamp":1760061699798,"version":"3.41.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,3,14]],"date-time":"2016-03-14T00:00:00Z","timestamp":1457913600000},"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":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s13735-016-0096-5","type":"journal-article","created":{"date-parts":[[2016,3,18]],"date-time":"2016-03-18T17:57:56Z","timestamp":1458323876000},"page":"105-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automatic environmental sound concepts discovery for video retrieval"],"prefix":"10.1007","volume":"5","author":[{"given":"Issam","family":"Feki","sequence":"first","affiliation":[]},{"given":"Anis","family":"Ben Ammar","sequence":"additional","affiliation":[]},{"given":"Adel M.","family":"Alimi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,3,14]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Saunders J, Lockheed Martin Co (1996) Real-time discrimination of broadcast speech\/music. In: IEEE International Conference on Acoustic, Speech, Signal Process, Atlanta, pp 993\u2013996","key":"96_CR1","DOI":"10.1109\/ICASSP.1996.543290"},{"doi-asserted-by":"crossref","unstructured":"Williams G, Ellis, Daniel PW (1999) Speech\/music discrimination based on posterior probability features. In: 6th European Conference on Speech Communication and Technology. Budapest","key":"96_CR2","DOI":"10.21437\/Eurospeech.1999-176x"},{"doi-asserted-by":"crossref","unstructured":"Scheirer E, Slaney M (1997) Construction and evaluation of a robust multifeature speech\/music discriminator. In: IEEE International Conferences on Acoust, Speech, Signal Process, Munich, pp 1331\u20131334","key":"96_CR3","DOI":"10.1109\/ICASSP.1997.596192"},{"issue":"3","key":"96_CR4","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/S0167-6393(02)00087-0","volume":"40","author":"J Ajmera","year":"2003","unstructured":"Ajmera J, McCowan I, Bourlard H (2003) Speech\/music segmentation using entropy and dynamism features in a HMM classification framework. Elsevier Speech Commun 40(3):351\u2013363","journal-title":"Elsevier Speech Commun"},{"issue":"4","key":"96_CR5","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/89.917689","volume":"9","author":"T Zhang","year":"2001","unstructured":"Zhang T, Kuo C-CJ (2001) Audio content analysis for online audiovisual data segmentation and classification. IEEE Trans Speech Audio Process 9(4):441\u2013457 Fall","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"1","key":"96_CR6","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":"3","key":"96_CR7","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/93.556537","volume":"3","author":"E Wold","year":"1996","unstructured":"Wold E, Blum T, Wheaton J (1996) Content-based classification, search and retrieval of audio. IEEE Trans Multimed 3(3):27\u201336","journal-title":"IEEE Trans Multimed"},{"key":"96_CR8","first-page":"509","volume":"5","author":"R Malkin","year":"2005","unstructured":"Malkin R, Waibel A (2005) Classifying user environments for mobile applications using linear autoencoding of ambient audio. Proc IEEE Int Conf Acoustic Speech Signal Process 5:509\u2013512","journal-title":"Proc IEEE Int Conf Acoustic Speech Signal Process"},{"issue":"2","key":"96_CR9","first-page":"1","volume":"3","author":"BL Milner","year":"2006","unstructured":"Milner BL, Smith D (2006) Acoustic environment classification. ACM Trans Speech Lang Process 3(2):1\u201322","journal-title":"ACM Trans Speech Lang Process"},{"unstructured":"Chu S, Narayanan S, Kuo C-CJ (2006) Content analysis for acoustic environment classification in mobile robots. In: International Conference on Aurally Informed Performance: Integrating Machine Listening and Auditory Presentation in Robotic System, Arlington, pp 16\u201321","key":"96_CR10"},{"doi-asserted-by":"crossref","unstructured":"Su F, Yang L, Lu T, Wang G (2011) Environmental sound classification for scene recognition using local discriminant bases and hmm. In: 19th ACM international conference on Multimedia, Newyork, pp 1389\u20131392","key":"96_CR11","DOI":"10.1145\/2072298.2072022"},{"doi-asserted-by":"crossref","unstructured":"Okuyucu C, Sert M, Yazici A (2013) Audio feature and classifier analysis for efficient recognition of environmental sounds. IEEE International Symposium on Multimedia. Anaheim, pp 125\u2013132","key":"96_CR12","DOI":"10.1109\/ISM.2013.29"},{"issue":"2","key":"96_CR13","first-page":"136","volume":"20","author":"X Xia-qing","year":"2013","unstructured":"Xia-qing X, Quan-wei B, Lei H, Xu W (2013) Study and application of semantic-based image retrieval. J China Univ Posts Telecommun 20(2):136\u2013142","journal-title":"J China Univ Posts Telecommun"},{"issue":"1","key":"96_CR14","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 automatic segmentation of continuous speech signals. IEEE Trans Acoustic Speech Signal Process 36(1):29\u201340","journal-title":"IEEE Trans Acoustic Speech Signal Process"},{"unstructured":"Thornburg H (2005) Detection and modeling of transient audio signals with prior information. Ph.D. dissertation, Stanford Univ., Stanford","key":"96_CR15"},{"doi-asserted-by":"crossref","unstructured":"Ellis DPP, Lee K (2004) Minimal-impact audio-based personal archives. 1st ACM Workshop Continuous Archiving and Recording of Personal Experiences CARPE-04, New York","key":"96_CR16","DOI":"10.1145\/1026653.1026659"},{"doi-asserted-by":"crossref","unstructured":"Lie Lu, Hanjalic A (2006) Audio elements based auditory scene segmentation. In: IEEE International Conference on Acoustic, Speech, Signal Process, Toulouse, France","key":"96_CR17","DOI":"10.1109\/ICASSP.2006.1661201"},{"doi-asserted-by":"crossref","unstructured":"Wichern G, Thornburg H, Mechtley B, Fink A, Tu K, Spanias A (2007) Robust multi-feature segmentation and indexing for natural sound environments. In: IEEE\/EURASIP International Workshop Content- Based Multimedia Indexing, Bordeaux, France, pp 69\u201376","key":"96_CR18","DOI":"10.1109\/CBMI.2007.385394"},{"doi-asserted-by":"crossref","unstructured":"Jafer E, Mahdi AE (2003) Wavelet based voiced\/unvoiced classification algorithm. EURASIP Conference focused on video\/ image processing and multimedia communications, pp 667\u2013672","key":"96_CR19","DOI":"10.1109\/VIPMC.2003.1220540"},{"issue":"4","key":"96_CR20","doi-asserted-by":"crossref","first-page":"515","DOI":"10.7763\/IJCEE.2012.V4.546","volume":"4","author":"I Feki","year":"2012","unstructured":"Feki I, Ben Ammar A, Alimi AM (2012) New process to identify audio concepts based on binary classifiers encapsulation. Int J Comp Elect Eng 4(4):515\u2013518","journal-title":"Int J Comp Elect Eng"},{"doi-asserted-by":"crossref","unstructured":"Feki I, Ben Ammar A, Alimi AM (2014) Query sound-by-example video retrieval framework. In: IEEE proceedings of International Conference on Hybrid Intelligent Systems, Kuwait, pp 297\u2013302","key":"96_CR21","DOI":"10.1109\/HIS.2014.7086165"},{"issue":"7","key":"96_CR22","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1109\/TIT.2004.830760","volume":"50","author":"N Vasconcelos","year":"2004","unstructured":"Vasconcelos N (2004) On the efficient evaluation of probabilistic similarity functions for image retrieval. IEEE Trans Inform Theory 50(7):1482\u20131496","journal-title":"IEEE Trans Inform Theory"},{"doi-asserted-by":"crossref","unstructured":"Hel\u00e9n M, Virtanen T (2007) Audio query by example of audio signals using Euclidean distance between Gaussian mixture models. IEEE International Conference on Audio, Speech and Signal Processing, Honolulu, USA, pp 225\u2013228","key":"96_CR23","DOI":"10.1109\/ICASSP.2007.366657"},{"issue":"3","key":"96_CR24","doi-asserted-by":"crossref","first-page":"821","DOI":"10.2298\/CSIS101012030Z","volume":"8","author":"J Zhao","year":"2011","unstructured":"Zhao J, Zhang Z, Han S, Qu C, Yuan Z, Zhang D (2011) SVM based forest fire detection using static and dynamic features. Comp Sci Inform Syst 8(3):821\u2013841","journal-title":"Comp Sci Inform Syst"},{"key":"96_CR25","volume-title":"Fundamentals of speech recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner L, Juang B (1993) Fundamentals of speech recognition. Prentice Hall, New Jersey"},{"unstructured":"Weitao W, Yuehui J, Tan Y, Yidong C (2012) A video quality assessment method using subjective and objective mapping stategy. In: IEEE International Conference on Cloud Computing and Intelligent Systems, vol 2, Hangzhou, pp 514\u2013518","key":"96_CR26"},{"doi-asserted-by":"crossref","unstructured":"Jadhav SM, Patil VS (2012) Review of significant researches on multimedia information retrieval. In: IEEE International Conference on Communication, Information and Computing Technology, Mumbai, pp 1\u20136","key":"96_CR27","DOI":"10.1109\/ICCICT.2012.6398155"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-016-0096-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13735-016-0096-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-016-0096-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T21:03:53Z","timestamp":1748811833000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13735-016-0096-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,14]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["96"],"URL":"https:\/\/doi.org\/10.1007\/s13735-016-0096-5","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"type":"print","value":"2192-6611"},{"type":"electronic","value":"2192-662X"}],"subject":[],"published":{"date-parts":[[2016,3,14]]}}}