{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:05:50Z","timestamp":1725807950163},"reference-count":37,"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\/icassp49357.2023.10097100","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":1,"title":["Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation"],"prefix":"10.1109","author":[{"given":"Bac","family":"Nguyen","sequence":"first","affiliation":[{"name":"Sony Europe B.V., R&#x0026;D Center,Stuttgart Laboratory 1,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Uhlich","sequence":"additional","affiliation":[{"name":"Sony Europe B.V., R&#x0026;D Center,Stuttgart Laboratory 1,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Cardinaux","sequence":"additional","affiliation":[{"name":"Sony Europe B.V., R&#x0026;D Center,Stuttgart Laboratory 1,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"ref7","first-page":"2530","article-title":"CLAR: Contrastive learning of auditory representations","volume-title":"AISTATS","author":"Al-Tahan"},{"article-title":"COALA: Coaligned autoencoders for learning semantically enriched audio representations","volume-title":"ICML","author":"Favory","key":"ref8"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415009"},{"key":"ref12","first-page":"21271","article-title":"Bootstrap your own latent: a new approach to self-supervised learning","volume-title":"NeurIPS","author":"Grill"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"ICLR","author":"Bardes","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747197"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"article-title":"Understanding dimensional collapse in contrastive self-supervised learning","volume-title":"ICLR","author":"Jing","key":"ref19"},{"article-title":"Reducing overfitting in deep networks by decorrelating representations","volume-title":"ICLR","author":"Cogswell","key":"ref20"},{"key":"ref21","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"ICML","author":"Wang"},{"article-title":"On feature diversity in energy-based models","volume-title":"W-ICLR","author":"Laakom","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"ref24","article-title":"The NTT DCASE2020 challenge task 6 system: Automated audio captioning with keywords and sentence length estimation","volume-title":"Tech. Rep., DCASE2020 Challenge","author":"Koizumi","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"Warden","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"year":"2018","key":"ref31","article-title":"Voxforge"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref34","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"ICML","author":"Engel"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768246"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10097100.pdf?arnumber=10097100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:05:03Z","timestamp":1705025103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097100","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}