{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T23:58:12Z","timestamp":1776729492083,"version":"3.51.2"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/taslp.2017.2738443","type":"journal-article","created":{"date-parts":[[2017,8,10]],"date-time":"2017-08-10T18:44:43Z","timestamp":1502390683000},"page":"1336-1351","source":"Crossref","is-referenced-by-count":31,"title":["Sound Event Recognition Using Auditory-Receptive-Field Binary Pattern and Hierarchical-Diving Deep Belief Network"],"prefix":"10.1109","volume":"26","author":[{"given":"Chien-Yao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andri","family":"Santoso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Chin","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref32","author":"o\u2019shaughnessy","year":"1987","journal-title":"Speech Communication Human and Machine"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.1945807"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.244"},{"key":"ref37","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref35","first-page":"2","article-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","author":"nakamura","year":"0","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/dac.2681"},{"key":"ref10","first-page":"1731","article-title":"Environmental sound classification using hybrid SVM\/KNN classifier and MPEG-7 audio low-level descriptor","author":"wang","year":"0","journal-title":"Proc IEEE Int Joint Conf Neural Netw"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854744"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041384"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857575"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2470119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2285131"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2100380"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854161"},{"key":"ref19","author":"moore","year":"2012","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853888"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959546"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262661"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"ref5","first-page":"5","article-title":"Acoustic event detection and classification in smart-room environments: Evaluation of CHIL project systems","author":"temko","year":"0","journal-title":"Proc IV Biennial Workshop Speech Technol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3831-1_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1026653.1026659"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118753"},{"key":"ref46","article-title":"Acoustic scene and event recognition using recurrent neural networks","author":"vu","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3335-0"},{"key":"ref45","article-title":"Gated recurrent networks applied to acoustic scene classification and acoustic event detection","author":"z\u00f6hrer","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694199"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2007.911680"},{"key":"ref42","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639360"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637760"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661400"},{"key":"ref44","article-title":"DCASE2016 baseline system","author":"heittola","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2303296"},{"key":"ref43","article-title":"Sound event detection in multichannel audio using spatial and harmonic features","author":"adavanne","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8356719\/08007276.pdf?arnumber=8007276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:21:58Z","timestamp":1642004518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8007276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2738443","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}