{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:41:30Z","timestamp":1780609290634,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952132","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T17:35:36Z","timestamp":1497980136000},"page":"131-135","source":"Crossref","is-referenced-by-count":1821,"title":["CNN architectures for large-scale audio classification"],"prefix":"10.1109","author":[{"given":"Shawn","family":"Hershey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sourish","family":"Chaudhuri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jort F.","family":"Gemmeke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aren","family":"Jansen","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":"Devin","family":"Platt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rif A.","family":"Saurous","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan","family":"Seybold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malcolm","family":"Slaney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701847"},{"key":"ref11","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":"ref12","author":"takahashi","year":"2016","journal-title":"Deep convolutional neural networks and data augmentation for acoustic event detection"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref14","article-title":"Trecvid 2016: Evaluating video search, video event detection, localization, and hyperlinking","author":"awad","year":"2016","journal-title":"Proceedings of TRECVID 2016"},{"key":"ref15","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity understanding","author":"fabian caba heilbron","year":"2015","journal-title":"Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref19","author":"eghbal-zadeh","year":"0","journal-title":"Cp-jku submissions for dcase-2016 A hybrid approach using binaural i-vectors and deep convolutional neural networks"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009000"},{"key":"ref4","author":"he","year":"2015","journal-title":"Deep residual learning for image recognition"},{"key":"ref27","first-page":"1","article-title":"Roc graphs: Notes and practical considerations for researchers","volume":"31","author":"fawcett","year":"2004","journal-title":"Machine Learning"},{"key":"ref3","author":"szegedy","year":"2015","journal-title":"Rethinking the inception architecture for computer vision"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Computer Vision and Pattern Recognition 2009 CVPR 2009 IEEE Conference on"},{"key":"ref29","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref8","first-page":"1267","article-title":"Acoustic event detection in real life recordings","author":"mesaros","year":"2010","journal-title":"18th European Signal Processing Conference 2010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.937498"},{"key":"ref2","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.02.005"},{"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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref22","author":"singhal","year":"2012","journal-title":"Introducing the Knowledge Graph Things Not Strings"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref24","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref23","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref26","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","author":"ioffe","year":"2015","journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift"}],"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\/07952132.pdf?arnumber=7952132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T07:25:07Z","timestamp":1569482707000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952132","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}