{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T03:05:15Z","timestamp":1785207915826,"version":"3.55.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952261","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"776-780","source":"Crossref","is-referenced-by-count":2204,"title":["Audio Set: An ontology and human-labeled dataset for audio events"],"prefix":"10.1109","author":[{"given":"Jort F.","family":"Gemmeke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan","family":"Freedman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aren","family":"Jansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wade","family":"Lawrence","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Channing","family":"Moore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manoj","family":"Plakal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marvin","family":"Ritter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Sound ontology for computational auditory scene analysis","author":"nakatani","year":"1998","journal-title":"Proceeding for the 1998 conference of the American Association for Artificial Intelligence"},{"key":"ref11","article-title":"Noisemes: Manual annotation of environmental noise in audio streams","author":"burger","year":"2012","journal-title":"Tech Rep CMU-LT I-12-07"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref13","author":"sager","year":"2016","journal-title":"Audiosentibank Large-scale semantic ontology of acoustic concepts for audio content analysis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/93.556537"},{"key":"ref15","first-page":"311","article-title":"Clear evaluation of acoustic event detection and classification systems","author":"temko","year":"2006","journal-title":"Classification of Events Activities and Relationships Evaluation and Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/992133.992154"},{"key":"ref19","author":"singhal","year":"2012","journal-title":"Introducing the Knowledge Graph Things Not Strings"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref3","author":"he","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.19.2.250"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.10.5.704"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-013-3430-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3758\/BF03193921"},{"key":"ref2","first-page":"1","article-title":"Going deeper with convolutions","author":"szegedy","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1207\/s15326969eco0501_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.11.035"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07952261.pdf?arnumber=7952261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,29]],"date-time":"2017-08-29T18:43:50Z","timestamp":1504032230000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952261","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}