{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T06:18:05Z","timestamp":1777184285712,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000308","name":"British Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000308","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096211","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["Simple Pooling Front-Ends for Efficient Audio Classification"],"prefix":"10.1109","author":[{"given":"Xubo","family":"Liu","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haohe","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhao","family":"Mei","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref12","article-title":"Low-complexity CNNs for acoustic scene classification","author":"singh","year":"2022","journal-title":"arXiv preprint 2208 01555"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747908"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10714"},{"key":"ref10","article-title":"Continual learning for on-device environmental sound classification","author":"xiao","year":"2022","journal-title":"arXiv preprint 2207 07429"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909575"},{"key":"ref17","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015714"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","first-page":"1021","article-title":"Speaker recognition from raw waveform with SincNet","author":"ravanelli","year":"2018","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2013.01.004"},{"key":"ref26","article-title":"Spectral representations for convolutional neural networks","volume":"28","author":"rippel","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"LEAF: A learnable frontend for audio classification","author":"zeghidour","year":"2021","journal-title":"arXiv 2101 08596"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.02.004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701857"},{"key":"ref21","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv preprint 1704"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref27","article-title":"TAU Urban Acoustic Scenes 2019, Development dataset","author":"heittola","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref3","article-title":"Speech Commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv preprint 1804 03209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857573"},{"key":"ref5","first-page":"1218","article-title":"Healthcare audio event classification using hidden Markov models and hierarchical hidden Markov models","author":"peng","year":"2009","journal-title":"IEEE International Conference on Multimedia"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096211.pdf?arnumber=10096211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:43Z","timestamp":1700506663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096211","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}