{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:50Z","timestamp":1730297210388,"version":"3.28.0"},"reference-count":38,"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\/slt54892.2023.10023407","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"245-251","source":"Crossref","is-referenced-by-count":0,"title":["Dual Learning for Large Vocabulary On-Device ASR"],"prefix":"10.1109","author":[{"given":"Cal","family":"Peyser","sequence":"first","affiliation":[{"name":"New York University,Center for Data Science,New York City,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google Inc.,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google Inc.,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google Inc.,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[{"name":"New York University,Center for Data Science,New York City,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyunghyun","family":"Cho","sequence":"additional","affiliation":[{"name":"New York University,Center for Data Science,New York City,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325953"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-122"},{"article-title":"Discrete autoencoders for sequence models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kaiser","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)","author":"Devlin","key":"ref8"},{"key":"ref9","article-title":"Improving transformer-based speech recognition using unsuper-vised pre-training","author":"Jiang","year":"2020","journal-title":"Interspeech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054458"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"Advancements in Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"volume-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","year":"2020","author":"Baevski","key":"ref14"},{"volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","year":"2020","author":"Baevski","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","article-title":"Dual learning for ma-chine translation","author":"He","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2703"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"article-title":"Almost unsupervised text to speech and automatic speech recognition","volume-title":"International Conference on Machine Learning (ICML)","author":"Ren","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746475"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref29","article-title":"On using monolin-gual corpora in neural machine translation","volume":"abs\/1503.03535","author":"Gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref32","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advancements in Neural Information Processing Systems (NeurIPS)"},{"key":"ref36","article-title":"On using monolin-gual corpora in neural machine translation","volume":"abs\/1503.03535","author":"Gulcehre","year":"2015","journal-title":"ArXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"}],"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\/10023407.pdf?arnumber=10023407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:10:48Z","timestamp":1707804648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023407","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}