{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:08:19Z","timestamp":1760710099612,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["108-2218-E-009-056","108-2321-B-075-004-MY2","108-2634-F-008-004"],"award-info":[{"award-number":["108-2218-E-009-056","108-2321-B-075-004-MY2","108-2634-F-008-004"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NCU and Pervasive Artificial Intelligence Research Labs, Taiwan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2964959","type":"journal-article","created":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T21:23:48Z","timestamp":1578518628000},"page":"1875-1887","source":"Crossref","is-referenced-by-count":15,"title":["Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks"],"prefix":"10.1109","volume":"28","author":[{"given":"Chien-Yao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tzu-Chiang","family":"Tai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0024-6732","authenticated-orcid":false,"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3899-750X","authenticated-orcid":false,"given":"Andri","family":"Santoso","sequence":"additional","affiliation":[]},{"given":"Seksan","family":"Mathulaprangsan","sequence":"additional","affiliation":[]},{"given":"Chin-Chin","family":"Chiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-2123","authenticated-orcid":false,"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"29493","article-title":"Learnt dictionary based active learning method for environmental sound event tagging","year":"2019","journal-title":"Multimedia Tools Appl"},{"key":"ref31","first-page":"99","article-title":"Audio data mining for anthropogenic disaster identification: An automatic taxonomy approach","author":"ye","year":"2017","journal-title":"IEEE Trans Emerg Topics Comput"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.05.011"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.32657\/10356\/59272","article-title":"Sound event recognition in unstructured environments using spectrogram image processing","author":"dennis","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2100380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref17","first-page":"197","article-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","author":"nakamura","year":"2000","journal-title":"Proc 2nd Int Conf Lang Res Eval"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226160"},{"key":"ref19","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262661"},{"key":"ref27","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref3","first-page":"5","article-title":"Acoustic event detection and classification in smartroom environments: Evaluation of CHIL project systems","volume":"65","author":"temko","year":"2006","journal-title":"Cough"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1026653.1026659"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref8","first-page":"1","article-title":"Twostep detection of water sound events for the diagnostic and monitoring of dementia","author":"guyot","year":"2013","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521503"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2285131"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959546"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637760"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref21","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738443"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_38"},{"article-title":"Gated recurrent networks applied to acoustic scene classification and acoustic event detection","year":"2016","author":"zhrer","key":"ref26"},{"article-title":"Sound event detection in multichannel audio using spatial and harmonic features","year":"2016","author":"adavanne","key":"ref25"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08952659.pdf?arnumber=8952659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8952659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2964959","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}