{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T21:11:21Z","timestamp":1770066681697,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icassp39728.2021.9414229","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"601-605","source":"Crossref","is-referenced-by-count":25,"title":["Efficient End-to-End Audio Embeddings Generation for Audio Classification on Target Applications"],"prefix":"10.1109","author":[{"given":"Paulo","family":"Lopez-Meyer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan A.","family":"del Hoyo Ontiveros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Stemmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"6590","article-title":"Implementation of efficient, low power deep neural networks on nextgeneration intel client platforms","author":"deisher","year":"2017","journal-title":"Proc IEEE ICASSP 2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.4"},{"key":"ref12","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref14","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"ref15","article-title":"Aclnet: efficient end-to-end audio classification CNN","author":"huang","year":"2018","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.33682\/8rd2-g787"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"CoRR"},{"key":"ref4","article-title":"Designing acoustic scene classification models with CNN variants","author":"suh","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref3","article-title":"Acoustic scene classification in dcase 2020 challenge: generalization across devices and low complexity solutions","author":"heittola","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020)"},{"key":"ref6","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"CoRR"},{"key":"ref5","article-title":"CP-JKU submissions to DCASE'20: Low- complexity cross-device acoustic scene classification with RF-regularized CNNs","author":"koutini","year":"2020","journal-title":"Tech Rep DCASE2020 Challenge"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.06.040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref1","article-title":"CNN architectures for large-scale audio classification","author":"hershey","year":"2016","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"}],"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\/09414229.pdf?arnumber=9414229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:56Z","timestamp":1652197256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414229","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}