{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:21:37Z","timestamp":1775229697267,"version":"3.50.1"},"reference-count":33,"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\/icassp43922.2022.9747432","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7667-7671","source":"Crossref","is-referenced-by-count":21,"title":["Performance-Efficiency Trade-Offs in Unsupervised Pre-Training for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Felix","family":"Wu","sequence":"first","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Kwangyoun","family":"Kim","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Jing","family":"Pan","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Kyu J.","family":"Han","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Kilian Q.","family":"Weinberger","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]},{"given":"Yoav","family":"Artzi","sequence":"additional","affiliation":[{"name":"ASAPP Inc."}]}],"member":"263","reference":[{"key":"ref33","article-title":"Fisher english training speech parts 1 and 2 transcripts ldc200{4,5}t19","author":"cieri","year":"2005","journal-title":"Web Download"},{"key":"ref32","article-title":"Fisher english training speech parts 1 and 2 ldc200{4,5}s13","author":"cieri","year":"2005","journal-title":"Web Download"},{"key":"ref31","article-title":"Sentence encoders on stilts: Supplementary training on intermediate labeled-data tasks","author":"phang","year":"2018"},{"key":"ref30","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"collobert","year":"2016"},{"key":"ref10","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref12","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref14","article-title":"Hubert: How much can a bad teacher benefit asr pre-training","author":"hsu","year":"2020","journal-title":"Workshop on Self-Supervised Learning for Speech and Audio Processing NeurIPS"},{"key":"ref15","article-title":"Lib-rispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-99579-3_21","article-title":"Ted-lium 3: twice as much data and corpus repartition for experiments on speaker adaptation","author":"hernandez","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref18","article-title":"Switchboard-1 release 2 ldc97s62","author":"godfrey","year":"1993","journal-title":"Web Download"},{"key":"ref19","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref3","article-title":"Self-training and pre-training are complementary for speech recognition","author":"xu","year":"2020"},{"key":"ref6","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref8","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"2019"},{"key":"ref7","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","author":"he","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1912"},{"key":"ref9","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref1","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020"},{"key":"ref20","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref22","volume":"33","author":"gumbel","year":"1954","journal-title":"Statistical Theory of Extreme Values and Some Practical Applications A Series of Lectures"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","article-title":"A* sampling","author":"maddison","year":"2014"},{"key":"ref23","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref25","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"}],"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\/09747432.pdf?arnumber=9747432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:12Z","timestamp":1660594032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747432","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}