{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:56:29Z","timestamp":1764402989260},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053051","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"source":"Crossref","is-referenced-by-count":49,"title":["Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model"],"prefix":"10.1109","author":[{"given":"Oleksii","family":"Hrinchuk","sequence":"first","affiliation":[{"name":"Moscow Institute of Physics and Technology,Moscow,Russia"}]},{"given":"Mariya","family":"Popova","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.03.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref15","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref17","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref6","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref9","article-title":"Adaptive input representations for neural language modeling","author":"baevski","year":"2019","journal-title":"ICLRE"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref20","article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","author":"ginsburg","year":"2019","journal-title":"arXiv preprint arXiv 1905 10520"},{"key":"ref22","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"arXiv preprint arXiv 1708 04552"},{"key":"ref21","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1426"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref26","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053051.pdf?arnumber=9053051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:25Z","timestamp":1659484645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053051","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}