{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T05:57:30Z","timestamp":1790402250814,"version":"4.1.0"},"reference-count":20,"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\/icassp39728.2021.9413482","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3035-3039","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Discriminative Learning of Sounds for Audio Event Classification"],"prefix":"10.1109","author":[{"given":"Sascha","family":"Hornauer","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stella X.","family":"Yu","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shabnam","family":"Ghaffarzadegan","sequence":"additional","affiliation":[{"name":"Robert Bosch LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Ren","sequence":"additional","affiliation":[{"name":"Robert Bosch LLC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_42"},{"key":"ref11","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Unsupervised feature learning for audio analysis","author":"meyer","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690563"},{"key":"ref15","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref17","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref19","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref3","article-title":"Esresnet: Environmental sound classification based on visual domain models","author":"guzhov","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2428998"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref7","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref9","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"}],"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\/09413482.pdf?arnumber=9413482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:17:55Z","timestamp":1659471475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413482","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}