{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T11:28:41Z","timestamp":1769167721840,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054725","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"146-150","source":"Crossref","is-referenced-by-count":3,"title":["End-To-End Auditory Object Recognition Via Inception Nucleus"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Ebrahimpour","sequence":"first","affiliation":[]},{"given":"Timothy","family":"Shea","sequence":"additional","affiliation":[]},{"given":"Andreea","family":"Danielescu","sequence":"additional","affiliation":[]},{"given":"David","family":"Noelle","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Kello","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref11","article-title":"Aclnet: efficient end-to-end audio classification cnn","author":"huang","year":"2018","journal-title":"arXiv preprint arXiv 1811 06669"},{"key":"ref12","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv preprint arXiv 1704 04861"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref18","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"AISTATS"},{"key":"ref19","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.488"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3320288.3320304"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref7","article-title":"Deep content-based music recommendation","author":"den oord","year":"2013","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553247"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref24","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682912"},{"key":"ref26","article-title":"Visualizing data using t-sne","author":"der maaten","year":"2008","journal-title":"JMLR"},{"key":"ref25","article-title":"Acoustic modeling with deep neural networks using raw time signal for lvcsr","author":"tuske","year":"2014","journal-title":"ACISCA"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054725.pdf?arnumber=9054725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:44Z","timestamp":1656375104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054725","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}