{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:34:21Z","timestamp":1753601661985,"version":"3.28.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022748","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"23-30","source":"Crossref","is-referenced-by-count":2,"title":["G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR"],"prefix":"10.1109","author":[{"given":"Gary","family":"Wang","sequence":"first","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ekin D.","family":"Cubuk","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyang","family":"Cheng","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quoc V.","family":"Le","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel S.","family":"Park","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-657"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438544"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404803"},{"key":"ref10","first-page":"21","article-title":"Vocal tract length per-turbation (vtlp) improves speech recognition","volume-title":"Proc. ICML Workshop on Deep Learning for Audio, Speech and Language","volume":"117","author":"Jaitly"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-207"},{"key":"ref13","article-title":"Autoaugment: Learning augmentation policies from data","author":"Cubuk","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Randaugment: Practical data augmentation with no separate search","author":"Cubuk","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2920"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"issue":"102","key":"ref18","first-page":"36","article-title":"Genetic algorithms in search, optimization, and machine learning","volume":"1989","author":"Golberg","year":"1989","journal-title":"Addion wesley"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1090.001.0001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Speechstew: Simply mix all avail-able speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Chime-6 chal-lenge: Tackling multispeaker speech recognition for unseg-mented recordings","author":"Watanabe","year":"2020","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref25","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":"Advances in Neural Infor-mation Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1470"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"ref29","first-page":"3239","article-title":"Learning to compose domain-specific transformations for data augmentation","author":"Ratner","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","author":"Ho","year":"2019","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Fast autoaugment","author":"Lim","year":"2019","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413928"},{"key":"ref35","article-title":"Improved regular-ization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv preprint"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref36"},{"volume-title":"Reading digits in natural images with unsupervised feature learning","year":"2011","author":"Netzer","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175355"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-007-9028-8"},{"key":"ref43","article-title":"Automated deep learning: Neural architecture search is not the end","author":"Dong","year":"2021","journal-title":"arXiv preprint"},{"issue":"3","key":"ref44","first-page":"193","article-title":"Genetic algorithms, tournament selection, and the effects of noise","volume":"9","author":"Miller","year":"1995","journal-title":"Complex sys-tems"},{"key":"ref45","article-title":"Pop-ulation based training of neural networks","author":"Jaderberg","year":"2017","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Com-mon voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref48","first-page":"125","article-title":"Ted-lium: an automatic speech recognition dedicated corpus","author":"Rousseau","year":"2012","journal-title":"LREC"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref53","first-page":"8007","article-title":"Automl-zero: Evolving machine learning algorithms from scratch","volume-title":"International Conference on Machine Learning","author":"Real"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022748.pdf?arnumber=10022748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:10:29Z","timestamp":1707804629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022748","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}