{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:31Z","timestamp":1775230111362,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746790","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"4593-4597","source":"Crossref","is-referenced-by-count":36,"title":["Towards Learning Universal Audio Representations"],"prefix":"10.1109","author":[{"given":"Luyu","family":"Wang","sequence":"first","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Pauline","family":"Luc","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Adri\u00e0","family":"Recasens","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Lucas","family":"Smaira","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Andrew","family":"Brock","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Andrew","family":"Jaegle","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Jean-Baptiste","family":"Alayrac","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Sander","family":"Dieleman","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"Joao","family":"Carreira","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]},{"given":"A\u00e4ron","family":"van den Oord","sequence":"additional","affiliation":[{"name":"DeepMind,London,UK"}]}],"member":"263","reference":[{"key":"ref10","article-title":"wav2vec2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref13","article-title":"Multi-format contrastive learning of audio representations","author":"wang","year":"2020","journal-title":"NeurIPS workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref15","article-title":"Contrastive learning of general-purpose audio representations","author":"saeed","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref18","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413376"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","article-title":"Characterizing signal propagation to close the performance gap in unnormalized resnets","author":"brock","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref6","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","author":"engel","year":"2017","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"ISMIR"},{"key":"ref8","article-title":"PANNs: Large-scale pretrained audio neural networks for audio pattern recognition","author":"kong","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref20","article-title":"High-performance large-scale image recognition without normalization","author":"brock","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref21","article-title":"Contrastive learning of musical representations","author":"spijkervet","year":"2021"},{"key":"ref24","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"Multimodal self-supervised learning of general audio representations","author":"wang","year":"2021"},{"key":"ref26","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref25","article-title":"Layer normalization","author":"ba","year":"2016"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746790.pdf?arnumber=9746790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:55:43Z","timestamp":1752774943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746790","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}