{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:22Z","timestamp":1730230642323,"version":"3.28.0"},"reference-count":24,"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\/icassp39728.2021.9414916","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3000-3004","source":"Crossref","is-referenced-by-count":2,"title":["Learning Separable Time-Frequency Filterbanks for Audio Classification"],"prefix":"10.1109","author":[{"given":"Jie","family":"Pu","sequence":"first","affiliation":[{"name":"Imperial College,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannis","family":"Panagakis","sequence":"additional","affiliation":[{"name":"University of Athens,Department of Informatics and Telecommunications,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref11","first-page":"373","article-title":"Spline filters for end-to-end deep learning","author":"balestriero","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-018-0127-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2918992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nn1536"},{"key":"ref15","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref17","first-page":"142","article-title":"Histogram of gradients of time–frequency representations for audio scene classification","volume":"23","author":"rakotomamonjy","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref18","article-title":"Auditory scene classification using machine learning techniques","author":"li","year":"2013","journal-title":"IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701890"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1651"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref2","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"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","article-title":"Ddsp: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref21","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref23","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09414916.pdf?arnumber=9414916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:16Z","timestamp":1659485956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414916","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}