{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:10:31Z","timestamp":1781050231128,"version":"3.54.1"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688018","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"251-258","source":"Crossref","is-referenced-by-count":18,"title":["Injecting Text in Self-Supervised Speech Pretraining"],"prefix":"10.1109","author":[{"given":"Zhehuai","family":"Chen","sequence":"first","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary","family":"Wang","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"220","article-title":"Intelligent selection of language model training data","author":"moore","year":"2010","journal-title":"Proceedings of the ACL 2010 Conference Short Papers"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref31","author":"sriram","year":"2017","journal-title":"Cold Fusion Training Seq2Seq Models Together with Language Models"},{"key":"ref30","author":"gulcehre","year":"2015","journal-title":"On using monolingual corpora in neural machine translation"},{"key":"ref37","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref36","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref28","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1475"},{"key":"ref22","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683602"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref50","article-title":"An efficient streaming non-recurrent on-device end-to-endmodel with improvements to rare-word modeling","author":"sainath","year":"0","journal-title":"InterSpeech"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref56","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"chan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref55","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","author":"shazeer","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref52","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref11","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"kihyuk","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref40","author":"wang","year":"2019","journal-title":"Contrastive sequence-to-sequence data selector"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1337"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-677"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref18","article-title":"Dual learning for machine translation","author":"he","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023627"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1891"},{"key":"ref8","article-title":"Speech simclr: Combining contrastive and reconstruction objective for self-supervised speech representation learning","author":"jiang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref46","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref47","article-title":"Improving tail performance of a deliberation e2e asr model using a largetext corpus","author":"peyser","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref42","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688018.pdf?arnumber=9688018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:24Z","timestamp":1652719344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688018","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}