{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:55:41Z","timestamp":1769752541720,"version":"3.49.0"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9415009","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"371-375","source":"Crossref","is-referenced-by-count":28,"title":["Unsupervised Contrastive Learning of Sound Event Representations"],"prefix":"10.1109","author":[{"given":"Eduardo","family":"Fonseca","sequence":"first","affiliation":[{"name":"Universitat Pompeu Fabra,Music Technology Group,Barcelona"}]},{"given":"Diego","family":"Ortego","sequence":"additional","affiliation":[{"name":"Dublin City University (DCU),Insight Centre for Data Analytics"}]},{"given":"Kevin","family":"McGuinness","sequence":"additional","affiliation":[{"name":"Dublin City University (DCU),Insight Centre for Data Analytics"}]},{"given":"Noel E.","family":"O'Connor","sequence":"additional","affiliation":[{"name":"Dublin City University (DCU),Insight Centre for Data Analytics"}]},{"given":"Xavier","family":"Serra","sequence":"additional","affiliation":[{"name":"Universitat Pompeu Fabra,Music Technology Group,Barcelona"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","author":"hendrycks","year":"2019","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref30","article-title":"Automatic shortcut removal for self-supervised representation learning","author":"minderer","year":"2020"},{"key":"ref10","article-title":"Improved base-lines with momentum contrastive learning","author":"chen","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937265"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref14","article-title":"Language agnostic speech embeddings for emotion classification","author":"nandan","year":"2020"},{"key":"ref15","article-title":"Data augmenting contrastive learning of speech representations in the time domain","author":"kharitonov","year":"2020"},{"key":"ref16","article-title":"Metric learning with background noise class for few-shot detection of rare sound events","author":"shimada","year":"2020","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref17","article-title":"Language Agnostic Speech Embed-dings for Emotion Classification","author":"nandan","year":"2020","journal-title":"Int Conf on Machine Learning Workshops (ICMLW)"},{"key":"ref18","article-title":"Self-Supervised Learning of Audio-Visual Objects from Video","author":"afouras","year":"2020","journal-title":"Eur Conf Comput Vision (ECCV)"},{"key":"ref19","article-title":"What Makes for Good Views for Contrastive Learning?","author":"tian","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081532"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937249"},{"key":"ref29","article-title":"Unsupervised Deep Learning by Neighbourhood Discovery","author":"huang","year":"2019","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3006378"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref2","article-title":"FSD50K: an Open Dataset of Human-Labeled Sound Events","author":"fonseca","year":"2020"},{"key":"ref9","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref22","article-title":"Freesound Datasets: a platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"Int Society for Music Inf Retrieval Conf (ISMIR 2017)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683158"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.33682\/j5zw-2t88"},{"key":"ref25","article-title":"General-purpose tagging of Freesound audio with AudioSet labels: task description, dataset, and baseline","author":"fonseca","year":"2018","journal-title":"Workshop on Detect and Classif of Acoust Scenes and Events (DCASE)"}],"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\/09415009.pdf?arnumber=9415009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:50Z","timestamp":1659485990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415009\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415009","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}