{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:32:53Z","timestamp":1725687173160},"reference-count":29,"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\/icassp49357.2023.10096146","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":0,"title":["Repackagingaugment: Overcoming Prediction Error Amplification in Weight-Averaged Speech Recognition Models Subject to Self-Training"],"prefix":"10.1109","author":[{"given":"Jae-Hong","family":"Lee","sequence":"first","affiliation":[{"name":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"arXiv preprint arXiv 1803 05407"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953162"},{"key":"ref15","article-title":"Stochastic weight averaging revisited","author":"guo","year":"2022","journal-title":"arXiv preprint arXiv 2201 00519"},{"key":"ref14","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","author":"garipov","year":"2018","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11460-011-0126-2"},{"key":"ref10","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2010 10504"},{"key":"ref2","article-title":"VQ-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"arXiv preprint arXiv 1910 05453"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref17","article-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","author":"wortsman","year":"2022","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","article-title":"Diverse weight averaging for out-of-distribution generalization","author":"ram\u00e9","year":"2022","journal-title":"arXiv preprint arXiv 2205 09739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref26","article-title":"Deep Speech: scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref20","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","article-title":"CTC-segmentation of large corpora for german end-to-end speech recognition","author":"k\u00fcrzinger","year":"2020","journal-title":"Proc International Conference on Speech and Computer (SPECOM)"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1679"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"}],"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\/10096146.pdf?arnumber=10096146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:55Z","timestamp":1699901875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096146","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}