{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:50:49Z","timestamp":1742644249253,"version":"3.28.0"},"reference-count":36,"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\/icassp43922.2022.9747805","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7202-7206","source":"Crossref","is-referenced-by-count":3,"title":["Word Order does not Matter for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Vineel","family":"Pratap","sequence":"first","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiantong","family":"Xu","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatiana","family":"Likhomanenko","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronan","family":"Collobert","sequence":"additional","affiliation":[{"name":"Facebook AI Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Word-level speech recognition with a letter to word encoder","author":"collobert","year":"2020","journal-title":"International Conference on Machine Learning ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682903"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"2020","journal-title":"8th International Conference on Learning Representations ICLR 2020 Addis Ababa Ethiopia"},{"article-title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","year":"2019","author":"synnaeve","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-571"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","year":"2020","author":"zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414058"},{"key":"ref16","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 information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1917"},{"key":"ref28","article-title":"Rethinking evaluation in asr: Are our models robust enough?","author":"likhomanenko","year":"2020","journal-title":"InterSpeech"},{"article-title":"Unsupervised speech recognition","year":"2021","author":"baevski","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-968"},{"article-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref29"},{"article-title":"Weakly supervised construction of asr systems with massive video data","year":"2020","author":"cheng","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-740"},{"key":"ref1","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"3","author":"lee","year":"2013","journal-title":"Workshop on Challenges in Representation Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414227"},{"key":"ref24","article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","author":"yeh","year":"2019","journal-title":"International Conference on Learning Representations"},{"article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","year":"2020","author":"liu","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2068"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747805.pdf?arnumber=9747805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:00Z","timestamp":1661184660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747805","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}