{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:13:54Z","timestamp":1771467234173,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461859","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"141-145","source":"Crossref","is-referenced-by-count":6,"title":["Enabling Early Audio Event Detection with Neural Networks"],"prefix":"10.1109","author":[{"given":"Huy","family":"Phan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Koch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ian","family":"McLoughlin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfred","family":"Mertins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177439"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref12","first-page":"6460","article-title":"Deep neural networks for automatic detection of screams and shouted speech in subway trains","author":"laffitte","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref13","author":"kumar","year":"2017","journal-title":"Deep CNN framework for audio event recognition using weakly labeled web data"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2367814"},{"key":"ref17","author":"phan","year":"2016","journal-title":"CaR-FOREST Joint classification-regression decision forests for overlapping audio event detection"},{"key":"ref18","author":"phan","year":"2017","journal-title":"DNN and CNN with weighted and multi-task loss functions for audio event detection"},{"key":"ref19","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 (JMLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-805"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"5","author":"\u00e7akir","year":"2017","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref6","year":"0","journal-title":"DCASE2016 Detection and classification of acoustic scenes and events"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref8","article-title":"DCASE 2017 challenge setup: tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE 2017)"},{"key":"ref7","year":"0","journal-title":"DCASE2016 Detection and classification of acoustic scenes and events"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0182309"},{"key":"ref9","article-title":"TUT database for acoustic scene classification and sound event detection","author":"mesaros","year":"2016","journal-title":"Proc EUSIPCO"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69568-4_29"},{"key":"ref21","author":"ruder","year":"2017","journal-title":"An overview of multi-task learning in deep neural networks"},{"key":"ref24","author":"ellis","year":"2009","journal-title":"Gammatone-like Spectrograms"},{"key":"ref23","author":"zieger","year":"2005","journal-title":"Acoustic event detection - ITC-irst AED database"},{"key":"ref26","article-title":"What makes audio event detection harder than classification?","author":"phan","year":"2017","journal-title":"EUSIPCO 2017"},{"key":"ref25","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461859.pdf?arnumber=8461859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:25:16Z","timestamp":1598221516000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461859","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}