{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:12:42Z","timestamp":1771611162774,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414641","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3030-3034","source":"Crossref","is-referenced-by-count":76,"title":["Self-Training and Pre-Training are Complementary for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Qiantong","family":"Xu","sequence":"first","affiliation":[]},{"given":"Alexei","family":"Baevski","sequence":"additional","affiliation":[]},{"given":"Tatiana","family":"Likhomanenko","sequence":"additional","affiliation":[]},{"given":"Paden","family":"Tomasello","sequence":"additional","affiliation":[]},{"given":"Alexis","family":"Conneau","sequence":"additional","affiliation":[]},{"given":"Ronan","family":"Collobert","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","article-title":"The challenge of realistic music generation: modelling raw audio at scale","author":"dieleman","year":"2018"},{"key":"ref30","article-title":"Categorical reparameterization with gumbel-softmax","volume":"abs 1611 1144","author":"jang","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref36","article-title":"Adaptive input representations for neural language modeling","author":"baevski","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"ref11","article-title":"Automatically generating extraction patterns from untagged text","author":"riloff","year":"1996","journal-title":"Proc Of AAAI"},{"key":"ref12","article-title":"Lessons from building acoustic models with a million hours of speech","author":"parthasarathi","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","volume":"abs 1807 3748","author":"v d oord","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref18","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref28","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","article-title":"Effectiveness of self-supervised pre-training for speech recognition","volume":"abs 1911 3912","author":"baevski","year":"2019"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2059","article-title":"Contextnet: Improving convolutional neural networks for automatic speech recognition with global context","author":"han","year":"2020"},{"key":"ref6","article-title":"Adversarial training of end-to-end speech recognition using a criticizing language model","author":"liu","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref5","article-title":"Ethnologue: Languages of the world, nineteenth edition","author":"lewis","year":"2016"},{"key":"ref8","article-title":"Semi-supervised speech recognition via local prior matching","author":"hsu","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref2","article-title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","volume":"abs 1911 8460","author":"synnaeve","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref20","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","volume":"abs 1910 9932","author":"jiang","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.findings-emnlp.106","article-title":"Learning robust and multilingual speech representations","author":"kawakami","year":"2020"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc of NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref26","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018"},{"key":"ref25","article-title":"Self-training improves pre-training for natural language understanding","author":"du","year":"2020"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414641.pdf?arnumber=9414641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T03:23:46Z","timestamp":1672111426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414641\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414641","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}