{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:54:57Z","timestamp":1776884097032,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094564","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation"],"prefix":"10.1109","author":[{"given":"Tsz Kin","family":"Lam","sequence":"first","affiliation":[{"name":"Heidelberg University,Computational Linguistics,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigehiko","family":"Schamoni","sequence":"additional","affiliation":[{"name":"Heidelberg University,Computational Linguistics,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Riezler","sequence":"additional","affiliation":[{"name":"Heidelberg University,Computational Linguistics,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1800"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1280"},{"key":"ref4","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-677"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-719"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1679"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.27"},{"key":"ref18","first-page":"10120","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","volume-title":"ICML. 2022, vol. 162 of Proceedings of Machine Learning Research","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.33"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","first-page":"4197","article-title":"Covost: A diverse multilingual speech-to-text translation corpus","volume-title":"Proceedings of LREC","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.150"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref25","first-page":"33","article-title":"Fairseq S2T: fast speech-to-text modeling with fairseq","volume-title":"Proceedings of AACL: System Demonstrations","author":"Wang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","volume-title":"Proceedings of ICLR (Poster)","author":"Kingma"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","first-page":"57","article-title":"On some pitfalls in automatic evaluation and significance testing for MT","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Riezler"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094564.pdf?arnumber=10094564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:07:43Z","timestamp":1710353263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094564","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}