{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T22:37:31Z","timestamp":1790635051322,"version":"4.1.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461353","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"336-340","source":"Crossref","is-referenced-by-count":23,"title":["Weighted and Multi-Task Loss for Rare Audio Event Detection"],"prefix":"10.1109","author":[{"given":"Huy","family":"Phan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Krawczyk-Becker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timo","family":"Gerkmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfred","family":"Mertins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","author":"phan","year":"2017","journal-title":"DNN and CNN with weighted and multi-task loss functions for audio event detection"},{"key":"ref31","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178831"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2367814"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2233470"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2025795"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2354236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2295918"},{"key":"ref18","first-page":"4037","article-title":"Parameterized MMSE spectral magnitude estimation for the enhancement of noisy speech","author":"breithaupt","year":"2008","journal-title":"IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref19","author":"ellis","year":"2009","journal-title":"Gammatone-like Spectrograms"},{"key":"ref28","first-page":"308","article-title":"Vocal tract length invariant features for automatic speech recognition","author":"mertins","year":"2005","journal-title":"Proc Automatic Speech Recognition and Understanding Workshop (ASRU)"},{"key":"ref4","author":"kumar","year":"2017","journal-title":"Deep cnn framework for audio event recognition using weakly labeled web data"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-123"},{"key":"ref29","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","author":"jaitly","year":"2013","journal-title":"Proc ICML 2013 Workshop on Deep Learning for Audio Speech and Language Processing"},{"key":"ref5","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":"ref8","first-page":"489","article-title":"Audio event detection from acoustic unit occurrence patterns","author":"kumar","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637759"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0182309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471667"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389618"},{"key":"ref20","author":"phan","year":"2016","journal-title":"CaR-FOREST Joint classification-regression decision forests for overlapping audio event detection"},{"key":"ref22","author":"ruder","year":"2017","journal-title":"An overview of multi-task learning in deep neural networks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177439"},{"key":"ref26","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref25","article-title":"TUT database for acoustic scene classification and sound event detection","author":"mesaros","year":"2016","journal-title":"Proc EUSIPCO"}],"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\/08461353.pdf?arnumber=8461353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:07:53Z","timestamp":1598245673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461353","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}