{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:25:07Z","timestamp":1771064707755,"version":"3.50.1"},"reference-count":38,"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\/icassp48485.2024.10446342","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"5435-5439","source":"Crossref","is-referenced-by-count":1,"title":["uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures"],"prefix":"10.1109","author":[{"given":"Afrina","family":"Tabassum","sequence":"first","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dung","family":"Tran","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,Applied Sciences Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trung","family":"Dang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,Applied Sciences Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismini","family":"Lourentzou","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,Applied Sciences Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref2","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Kenton","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref7","article-title":"Masked autoencoders that listen","author":"Huang","year":"2022","journal-title":"NeurIPS"},{"key":"ref8","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2023","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref16","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"ICLR"},{"key":"ref17","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref18","author":"Epstein","year":"2019","journal-title":"Generalization bounds for unsupervised and semi-supervised learning with autoencoders"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28078"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref24","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","author":"Niizumi","year":"2022","journal-title":"HEAR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref28","article-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018","journal-title":"ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref30","article-title":"i-Mix: A domain-agnostic strategy for contrastive representation learning","author":"Lee","year":"2021","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref35","author":"Warden","year":"2018","journal-title":"Speech commands: A dataset for limitedvocabulary speech recognition"},{"key":"ref36","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"Engel","year":"2017","journal-title":"ICML"},{"key":"ref37","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"Fonseca","year":"2018","journal-title":"DCASE"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref39","article-title":"Visualizing data using tsne","author":"Van der Maaten","year":"2008","journal-title":"JMLR"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446342.pdf?arnumber=10446342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:50Z","timestamp":1722573530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446342","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}