{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:21:33Z","timestamp":1753600893244},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10626360","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"680-684","source":"Crossref","is-referenced-by-count":1,"title":["Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning"],"prefix":"10.1109","author":[{"given":"Alain","family":"Riou","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lattner","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ga\u00ebtan","family":"Hadjeres","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoffroy","family":"Peeters","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"article-title":"Representation Learning with Contrastive Predictive Coding","year":"2018","author":"Van den Oord","key":"ref3"},{"article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","year":"2022","author":"Baevski","key":"ref8"},{"key":"ref9","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10126"},{"article-title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","volume-title":"PMLR","author":"Niizumi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"ICML","author":"Wang","key":"ref14"},{"article-title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","volume-title":"ICML","author":"Zbontar","key":"ref15"},{"article-title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","volume-title":"ICLR","author":"Bardes","key":"ref16"},{"article-title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","year":"2021","author":"Tian","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3221007"},{"article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference","author":"Devlin","key":"ref20"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","key":"ref21"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1145\/2733373.2806390","article-title":"ESC: Dataset for Environmental Sound Classification","volume-title":"Proceedings of the 23rd Annual ACM Conference on Multimedia","author":"Piczak"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref24","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref27","article-title":"Automatic musical genre classification of audio signals","author":"Tzanetakis","year":"2001","journal-title":"ISMIR"},{"article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"ICML","author":"Engel","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768246"},{"key":"ref30","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","year":"2022","author":"Dao","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","key":"ref33"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626360.pdf?arnumber=10626360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:31:20Z","timestamp":1723786280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626360","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}