{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:25:45Z","timestamp":1786476345544,"version":"3.56.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414551","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"611-615","source":"Crossref","is-referenced-by-count":18,"title":["Multi-View Audio And Music Classification"],"prefix":"10.1109","author":[{"given":"Huy","family":"Phan","sequence":"first","affiliation":[{"name":"Queen Mary University of London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huy","family":"Le Nguyen","sequence":"additional","affiliation":[{"name":"HCMC University of Technology,Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver Y.","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Oxford,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lam","family":"Pham","sequence":"additional","affiliation":[{"name":"Austrian Institute of Technology Vienna,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Koch","sequence":"additional","affiliation":[{"name":"University of Lübeck,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"McLoughlin","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfred","family":"Mertins","sequence":"additional","affiliation":[{"name":"University of Lübeck,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240631"},{"key":"ref30","article-title":"Convolutional neural network with multiple-width frequency-delta data augmentation for acoustic scene classification","author":"han","year":"2016","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref11","article-title":"Comparison of time-frequency representations for environmental sound classification using convolutional neural networks","author":"huzaifah","year":"2017"},{"key":"ref12","first-page":"1032","article-title":"Cqt-based convolutional neural networks for audio scene classification","author":"lidy","year":"2016","journal-title":"DCASE 2016 Technical Report"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref14","article-title":"Learning from between-class examples for deep sound recognition","author":"harada","year":"2018","journal-title":"Proc ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01203-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2020.102943"},{"key":"ref17","article-title":"What makes training multi-modal networks hard?","author":"wang","year":"2020","journal-title":"Proc CVPR"},{"key":"ref18","article-title":"XSleepNet: Multi-view sequential model for automatic sleep staging","author":"phan","year":"2020"},{"key":"ref19","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref28","article-title":"Bottom-up broadcast neural network for music genre classification","author":"liu","year":"2019","journal-title":"Pattern Recognition Letters"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1219"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref29","article-title":"ESResNet: Environmental sound classification based on visual domain models","author":"guzhov","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939495"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref24","article-title":"Constant-q transform tool-box for music processing","author":"schoerkhuber","year":"2010","journal-title":"Proc 7th Sound and Music Computing Conference"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref26","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc International Conference on Learning Representations (ICLR)"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"Librosa: Audio and music signal analysis in python","author":"mcfee","year":"2015","journal-title":"Proc 14th Python in Science Conference"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414551.pdf?arnumber=9414551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:06Z","timestamp":1659485886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414551","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}