{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T03:03:48Z","timestamp":1772507028900,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095041","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Audio Barlow Twins: Self-Supervised Audio Representation Learning"],"prefix":"10.1109","author":[{"given":"Jonah","family":"Anton","sequence":"first","affiliation":[{"name":"Imperial College,London,UK"}]},{"given":"Harry","family":"Coppock","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}]},{"given":"Pancham","family":"Shukla","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume":"abs 2103 3230","author":"zbontar","year":"2021","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref15","first-page":"1","article-title":"A note on connecting barlow twins with negative-sample-free contrastive learning","author":"tsai","year":"2021"},{"key":"ref14","first-page":"1","article-title":"Exploring simple siamese representation learning","volume":"abs 2011 10566","author":"chen","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref10","first-page":"1","article-title":"ibot: Image BERT pre-training with online tokenizer","volume":"abs 2111 7832","author":"zhou","year":"2021","journal-title":"CoRR"},{"key":"ref2","first-page":"1","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume":"abs 2006 7733","author":"grill","year":"2020","journal-title":"CoRR"},{"key":"ref1","first-page":"1","article-title":"A simple framework for contrastive learning of visual representations","volume":"abs 2002 5709","author":"chen","year":"2020","journal-title":"CoRR"},{"key":"ref17","first-page":"2","article-title":"Unsupervised contrastive learning of sound event representations","author":"fonseca","year":"2020"},{"key":"ref16","first-page":"1","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume":"abs 2102 6810","author":"tian","year":"2021","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref18","first-page":"1","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"abs 2006 9882","author":"caron","year":"2020","journal-title":"CoRR"},{"key":"ref24","first-page":"3","article-title":"Early convolutions help transformers see better","volume":"abs 2106 14881","author":"xiao","year":"2021","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","first-page":"3","article-title":"Byol-s: Learning self-supervised speech representations by bootstrapping","author":"elbanna","year":"2022"},{"key":"ref25","first-page":"3","article-title":"Hear: Holistic evaluation of audio representations","author":"turian","year":"2022"},{"key":"ref20","first-page":"2","article-title":"Clar: Contrastive learning of auditory representations","author":"al-tahan","year":"2020"},{"key":"ref22","first-page":"2","article-title":"Byol for audio: Exploring pre-trained general-purpose audio representations","author":"niizumi","year":"2022"},{"key":"ref21","first-page":"2","article-title":"The ntt dcase2020 challenge task 6 system: Automated audio captioning with keywords and sentence length estimation","author":"koizumi","year":"2020"},{"key":"ref28","first-page":"3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"abs 2006 11477","author":"baevski","year":"2020","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref8","first-page":"1","article-title":"SSAST: self-supervised audio spectrogram transformer","volume":"abs 2110 9784","author":"gong","year":"2021","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref9","first-page":"1","article-title":"Masked autoencoders that listen","author":"huang","year":"2022"},{"key":"ref4","first-page":"1","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","first-page":"1","article-title":"Contrastive learning of general-purpose audio representations","volume":"abs 2010 10915","author":"saeed","year":"2020","journal-title":"CoRR"},{"key":"ref5","first-page":"1","article-title":"Roberta: A robustly optimized BERT pre-training approach","volume":"abs 1907 11692","author":"liu","year":"2019","journal-title":"CoRR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095041.pdf?arnumber=10095041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T17:26:08Z","timestamp":1714584368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095041","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}