{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:47:57Z","timestamp":1730231277746,"version":"3.28.0"},"reference-count":32,"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\/icasspw59220.2023.10193076","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:54Z","timestamp":1690983054000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Unfused: Unsupervised Finetuning Using Self Supervised Distillation"],"prefix":"10.1109","author":[{"given":"Ashish","family":"Seth","sequence":"first","affiliation":[{"name":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sreyan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Umesh","sequence":"additional","affiliation":[{"name":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"volume-title":"A multi-device dataset for urban acoustic scene classification","year":"2018","author":"Mesaros","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3202093"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref10","article-title":"Self-distillation for further pre-training of transformers","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv:2210.02871"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"journal-title":"Free speech... recognition (linux, windows and mac)-voxforge.org","year":"2014","key":"ref12"},{"key":"ref13","article-title":"Deep clustering for general-purpose audio representations","author":"Ghosh","year":"2021","journal-title":"arXiv preprint arXiv:2110.08895"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096796"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746529"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref20","article-title":"Revisiting self-distillation","author":"Pham","year":"2022","journal-title":"arXiv preprint arXiv:2206.08491"},{"key":"ref21","article-title":"The ntt dcase2020 challenge task 6 system: Automated audio captioning with keywords and sentence length estimation","author":"Koizumi","year":"2020","journal-title":"arXiv preprint arXiv:2007.00225"},{"key":"ref22","article-title":"Effects of word-frequency based pre-and post-processings for audio captioning","author":"Takeuchi","year":"2020","journal-title":"arXiv preprint arXiv:2009.11436"},{"key":"ref23","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3133208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"volume-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"Warden","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref29","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"ICML","author":"Engel","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.13103"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"}],"event":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10192576\/10192577\/10193076.pdf?arnumber=10193076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:47:47Z","timestamp":1710370067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icasspw59220.2023.10193076","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}