{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:13:59Z","timestamp":1782386039059,"version":"3.54.5"},"reference-count":36,"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\/icassp39728.2021.9413528","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3875-3879","source":"Crossref","is-referenced-by-count":169,"title":["Contrastive Learning of General-Purpose Audio Representations"],"prefix":"10.1109","author":[{"given":"Aaqib","family":"Saeed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Grangier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Zeghidour","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Voxforge","author":"maclean","year":"2018","journal-title":"Ken MacLean"},{"key":"ref32","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref31","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13103"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref35","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref34","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019"},{"key":"ref10","article-title":"Unsupervised feature learning for audio analysis","author":"meyer","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1107"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref16","article-title":"Self-supervised audio representation learning for mobile devices","author":"tagliasacchi","year":"2019"},{"key":"ref17","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref28","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref4","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"ECCV"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref3","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref29","article-title":"Tut urban acoustic scenes 2018, development dataset","author":"heittola","year":"2018"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.findings-emnlp.106","article-title":"Learning robust and multilingual speech representations","author":"kawakami","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref7","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref2","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472647"},{"key":"ref1","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","article-title":"Data augmenting contrastive learning of speech representations in the time domain","author":"kharitonov","year":"2020"},{"key":"ref21","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref23","article-title":"Unsupervised feature learning via non-parametric instance-level discrimination","author":"wu","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"}],"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\/09413528.pdf?arnumber=9413528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:25:35Z","timestamp":1672129535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413528","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}