{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:46:08Z","timestamp":1761597968718,"version":"3.41.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,7,25]],"date-time":"2018-07-25T00:00:00Z","timestamp":1532476800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY18F010008"],"award-info":[{"award-number":["LY18F010008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009193","name":"Marsden Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009193","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1007\/s11042-018-6380-z","type":"journal-article","created":{"date-parts":[[2018,7,25]],"date-time":"2018-07-25T06:05:48Z","timestamp":1532498748000},"page":"3831-3842","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Dictionary-based active learning for sound event classification"],"prefix":"10.1007","volume":"78","author":[{"given":"Wanting","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,25]]},"reference":[{"issue":"11","key":"6380_CR1","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1016\/j.apacoust.2011.05.008","volume":"72","author":"BD Barkana","year":"2011","unstructured":"Barkana BD, Uzkent B (2011) Environmental noise classifier using a new set of feature parameters based on pitch range. Appl Acoust 72(11):841\u2013848","journal-title":"Appl Acoust"},{"issue":"6","key":"6380_CR2","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TASL.2009.2017438","volume":"17","author":"S Chu","year":"2009","unstructured":"Chu S, Narayanan S, Jay Kuo C-C (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"},{"issue":"2","key":"6380_CR3","first-page":"201","volume":"15","author":"D Cohn","year":"1994","unstructured":"Cohn D, Atlas L, Ladner R (1994) Improving generalization with active learning. Mach Learn 15(2):201\u2013221","journal-title":"Mach Learn"},{"issue":"4","key":"6380_CR4","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/s10462-012-9362-y","volume":"42","author":"S Duan","year":"2012","unstructured":"Duan S, Zhang J, Roe P, Towsey M (2012) A survey of tagging techniques for music, speech and environmental sound. Artif Intell Rev 42(4):637\u2013661","journal-title":"Artif Intell Rev"},{"key":"6380_CR5","doi-asserted-by":"crossref","unstructured":"Fleury A, Noury N, Vacher M, Glasson H, Seri JF (2008) Sound and speech detection and classification in a health smart home. In: Proc. IEEE Int. Conf. Engineering in Medicine and Biology Society, p 4644\u20134647","DOI":"10.1109\/IEMBS.2008.4650248"},{"issue":"1","key":"6380_CR6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TITS.2015.2470216","volume":"17","author":"P Foggia","year":"2016","unstructured":"Foggia P, Petkov N, Saggese A, Strisciuglio N, Vento M (2016) Audio surveillance of roads: a system for detecting anomalous sounds. IEEE Trans Intell Transp Syst 17(1):279\u2013288","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6380_CR7","doi-asserted-by":"crossref","unstructured":"Gadde A, Anis A, Ortega A (2014) Active semi-supervised learning using sampling theory for graph signals. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, p 492\u2013501","DOI":"10.1145\/2623330.2623760"},{"key":"6380_CR8","unstructured":"Ghofrani S, McLernon DC, Ayatollahi A (2003) Comparing Gaussian and chirplet dictionaries for time-frequency analysis using matching pursuit decomposition. In: Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on. IEEE, p 713\u2013716"},{"key":"6380_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/9781118142882","volume-title":"Speech and audio signal processing: processing and perception of speech and music","author":"B Gold","year":"2011","unstructured":"Gold B, Morgan N, Ellis D (2011) Speech and audio signal processing: processing and perception of speech and music. Wiley, Hoboken"},{"issue":"9","key":"6380_CR10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0162075","volume":"11","author":"W Han","year":"2016","unstructured":"Han W, Coutinho E, Ruan H, Li H, Schuller B, Yu X, Zhu X (2016) Semi-supervised active learning for sound classification in hybrid learning environments. PLoS One 11(9):e0162075","journal-title":"PLoS One"},{"key":"6380_CR11","unstructured":"Krogh A, Vedelsby J (1995) Neural network ensembles, cross validation, and active learning. In: Advances in neural information processing systems, p 231\u2013238"},{"key":"6380_CR12","unstructured":"Lei C, Zhu X (2017) Unsupervised feature selection via local structure learning and sparse learning. Multimedia Tools and Appl: 1\u201318"},{"key":"6380_CR13","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.apacoust.2017.08.006","volume":"129","author":"P Maijala","year":"2018","unstructured":"Maijala P, Shuyang Z, Heittola T, Virtanen T (2018) Environmental noise monitoring using source classification in sensors. Appl Acoust 129:258\u2013267","journal-title":"Appl Acoust"},{"issue":"12","key":"6380_CR14","doi-asserted-by":"publisher","first-page":"3397","DOI":"10.1109\/78.258082","volume":"41","author":"SG Mallat","year":"1993","unstructured":"Mallat SG, Zhang Z (1993) Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process 41(12):3397\u20133415","journal-title":"IEEE Trans Signal Process"},{"issue":"2","key":"6380_CR15","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.specom.2006.11.004","volume":"49","author":"D Morrison","year":"2007","unstructured":"Morrison D, Wang R, De Silva LC (2007) Ensemble methods for spoken emotion recognition in call-centres. Speech Comm 49(2):98\u2013112","journal-title":"Speech Comm"},{"issue":"2","key":"6380_CR16","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1016\/j.eswa.2008.01.039","volume":"36","author":"H-S Park","year":"2009","unstructured":"Park H-S, Jun C-H (2009) A simple and fast algorithm for K-medoids clustering. Expert Syst Appl 36(2):3336\u20133341","journal-title":"Expert Syst Appl"},{"key":"6380_CR17","unstructured":"Phuong NC, Dat TD (2013) Sound classification for event detection: Application into medical telemonitoring. In: Proc. Int. Conf. Computing, Management and Telecommunications (ComManTel), p 330\u2013333"},{"key":"6380_CR18","doi-asserted-by":"crossref","unstructured":"Piczak KJ (2015) ESC: dataset for environmental sound classification. In: Proc. ACM Int. Conf. Multimedia, p 1015\u20131018","DOI":"10.1145\/2733373.2806390"},{"issue":"3","key":"6380_CR19","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TMM.2016.2618218","volume":"19","author":"J Ren","year":"2017","unstructured":"Ren J, Jiang X, Yuan J, Magnenat-Thalmann N (2017) Sound-event classification using robust texture features for robot hearing. IEEE Trans Multimedia 19(3):447\u2013458","journal-title":"IEEE Trans Multimedia"},{"issue":"4","key":"6380_CR20","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TSA.2005.848882","volume":"13","author":"G Riccardi","year":"2005","unstructured":"Riccardi G, Hakkani-Tur D (2005) Active learning: theory and applications to automatic speech recognition. IEEE Trans Speech Audio Process 13(4):504\u2013511","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"6","key":"6380_CR21","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1109\/JPROC.2010.2040551","volume":"98","author":"R Rubinstein","year":"2010","unstructured":"Rubinstein R, Bruckstein AM, Elad M (2010) Dictionaries for sparse representation modeling. Proc IEEE 98(6):1045\u20131057","journal-title":"Proc IEEE"},{"key":"6380_CR22","doi-asserted-by":"crossref","unstructured":"Salamon J, Jacoby C, Bello JP (2014) A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM international conference on Multimedia. ACM, p. 1041\u20131044","DOI":"10.1145\/2647868.2655045"},{"key":"6380_CR23","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der J, Anemiiller J, Goetze S (2016) Classification of human cough signals using spectro-temporal Gabor filterbank features. In: Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on. IEEE, p. 6455\u20136459","DOI":"10.1109\/ICASSP.2016.7472920"},{"key":"6380_CR24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.ins.2017.02.013","volume":"396","author":"RV Sharan","year":"2017","unstructured":"Sharan RV, Moir TJ (2017) Robust acoustic event classification using deep neural networks. Inf Sci 396:24\u201332","journal-title":"Inf Sci"},{"key":"6380_CR25","doi-asserted-by":"crossref","unstructured":"Shuyang Z, Heittola T, Virtanen T (2017) Active learning for sound event classification by clustering unlabeled data. In: Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on, p 751\u2013755","DOI":"10.1109\/ICASSP.2017.7952256"},{"key":"6380_CR26","doi-asserted-by":"crossref","unstructured":"Sugden P, Canagarajah N (2004) Underdetermined noisy blind separation using dual matching pursuits. In: Acoustics, Speech, and Signal Processing (ICASSP'04). IEEE International Conference on, vol. 5, p V-557. IEEE","DOI":"10.1109\/ICASSP.2004.1327171"},{"issue":"3","key":"6380_CR27","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/LSP.2003.822904","volume":"11","author":"P Vera-Candeas","year":"2004","unstructured":"Vera-Candeas P, Ruiz-Reyes N, Rosa-Zurera M, Martinez-Munoz D, L\u00f3pez-Ferreras F (2004) Transient modeling by matching pursuits with a wavelet dictionary for parametric audio coding. IEEE Signal Process Lett 11(3):349\u2013352","journal-title":"IEEE Signal Process Lett"},{"key":"6380_CR28","doi-asserted-by":"publisher","unstructured":"Wang R, Zong M (2018) Unsupervised feature selection based on self-representation and subspace learning. World Wide Web. https:\/\/doi.org\/10.1007\/s11280-017-0508-3","DOI":"10.1007\/s11280-017-0508-3"},{"issue":"2","key":"6380_CR29","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1109\/TASE.2013.2285131","volume":"11","author":"J-C Wang","year":"2014","unstructured":"Wang J-C, Lin C-H, Chen B-W, Tsai M-K (2014) Gabor-based nonuniform scale-frequency map for environmental sound classification in home automation. IEEE Trans Autom Sci Eng 11(2):607\u2013613","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"6380_CR30","unstructured":"Wang C-Y, Wang J-C, Santoso A, Chiang C-C, Wu C-H (2017) Sound event recognition using auditory-receptive-field binary pattern and hierarchical-diving deep belief network. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, p 1\u201316"},{"key":"6380_CR31","doi-asserted-by":"crossref","unstructured":"Wang R, Ji W, Liu M, Wang X, Weng J, Deng S, Gao S, Yuan C-a. (2018) Review on mining data from multiple data sources. Pattern Recogn Lett","DOI":"10.1016\/j.patrec.2018.01.013"},{"key":"6380_CR32","doi-asserted-by":"crossref","unstructured":"Zhang Z, Schuller B (2012) Semi-supervised learning helps in sound event classification. In: Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, p 333\u2013336","DOI":"10.1109\/ICASSP.2012.6287884"},{"key":"6380_CR33","doi-asserted-by":"crossref","unstructured":"Zhang S, Li X, Zong M, Zhu X, Wang R (2017) Efficient knn classification with different numbers of nearest neighbors. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2017.2673241"},{"key":"6380_CR34","unstructured":"Zheng W, Zhu X, Zhu Y, Hu R, Lei C (2017) Dynamic graph learning for spectral feature selection. Multimed Tools Appl: 1\u201317"},{"key":"6380_CR35","unstructured":"Zhu X (2006) Semi-supervised learning literature survey. University of Wisconsin-Madison, Technical Report 1530, Wisconsin"},{"issue":"3","key":"6380_CR36","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1109\/TKDE.2017.2763618","volume":"30","author":"X Zhu","year":"2018","unstructured":"Zhu X, Zhang S, Hu R, Zhu Y (2018) Local and global structure preservation for robust unsupervised spectral feature selection. IEEE Trans Knowl Data Eng 30(3):517\u2013529","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6380-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6380-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6380-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:55:19Z","timestamp":1751763319000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6380-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,25]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["6380"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6380-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2018,7,25]]},"assertion":[{"value":"5 November 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}