{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T22:26:26Z","timestamp":1772749586972,"version":"3.50.1"},"reference-count":37,"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\/icassp43922.2022.9746490","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8862-8866","source":"Crossref","is-referenced-by-count":8,"title":["Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks"],"prefix":"10.1109","author":[{"given":"Sangeeta","family":"Srivastava","sequence":"first","affiliation":[{"name":"The Ohio State University,USA"}]},{"given":"Yun","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]},{"given":"Andros","family":"Tjandra","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Reality Labs Research,USA"}]},{"given":"Chunxi","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]},{"given":"Kritika","family":"Singh","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]},{"given":"Yatharth","family":"Saraf","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref32","article-title":"PSLA: Improving audio event classification with pretraining, sampling, labeling, and aggregation","author":"gong","year":"2021"},{"key":"ref31","article-title":"Multimodal self-supervised learning of general audio representations","author":"wang","year":"2021"},{"key":"ref30","first-page":"7","article-title":"Self-supervised multimodal versatile networks","volume":"2","author":"alayrac","year":"2020","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Contrastive learning of musical representations","author":"spijkervet","year":"2021"},{"key":"ref36","article-title":"ERANNs: Efficient residual audio neural networks for audio pattern recognition","author":"verbitskiy","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref34","first-page":"5447","article-title":"A sequential self teaching approach for improving generalization in sound event recognition","author":"kumar","year":"2020","journal-title":"ICML"},{"key":"ref10","first-page":"100","article-title":"Convolution-augmented transformer for semisupervised sound event detection","author":"miyazaki","year":"2020","journal-title":"DCAS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-347"},{"key":"ref12","first-page":"776","article-title":"Audio Set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"},{"key":"ref18","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018"},{"key":"ref19","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"ISMIR"},{"key":"ref28","article-title":"Multi-format contrastive learning of audio representations","author":"wang","year":"2021"},{"key":"ref4","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"akbari","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1891"},{"key":"ref3","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Improved language identification through cross-lingual self-supervised learning","author":"tjandra","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632739"},{"key":"ref5","article-title":"CL4AC: A contrastive loss for audio captioning","author":"liu","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref7","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"fan","year":"2020"},{"key":"ref2","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref9","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020"},{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref24","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054137"}],"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\/09746490.pdf?arnumber=9746490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:28Z","timestamp":1661199088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746490","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}