{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:56:00Z","timestamp":1730199360778,"version":"3.28.0"},"reference-count":32,"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\/asru51503.2021.9688249","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"817-823","source":"Crossref","is-referenced-by-count":1,"title":["Learning to Translate Low-Resourced Swiss German Dialectal Speech into Standard German Text"],"prefix":"10.1109","author":[{"given":"Abbas","family":"Khosravani","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Switzerland"}]},{"given":"Philip N.","family":"Garner","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}]},{"given":"Alexandros","family":"Lazaridis","sequence":"additional","affiliation":[{"name":"Data, Analytics & AI Group - Swisscom AG,Switzerland"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref11","first-page":"7180","article-title":"Leveraging weakly supervised data to improve end-to-end speech-to-text translation","author":"ye","year":"2019","journal-title":"ICASSP 2019–2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6452"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1835"},{"key":"ref15","first-page":"116","article-title":"Machine translation of speech","volume":"6","author":"stentiford","year":"1988","journal-title":"British Telecom Technology Journal"},{"key":"ref16","first-page":"1357","article-title":"Modeling with structures in statistical machine translation","volume":"2","author":"wang","year":"0","journal-title":"36th Annual Meeting of the Association for Computational Lin-guistics and 17th International Conference on Compu-tational Linguistics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1075671.1075718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-32"},{"key":"ref19","article-title":"Spoken language translation using automatically transcribed text in training","author":"peitz","year":"0","journal-title":"International Workshop on Spoken Language Translation (IWSLT) 2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.29007\/62b2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref27","first-page":"6000","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref6","article-title":"Germeval 2020 task 4: Low-resource speech-to-text","author":"pl\u00fcss","year":"0","journal-title":"SwissText\/KONVENS"},{"key":"ref29","first-page":"16","article-title":"Speech recognition and keyword spot-ting for low-resource languages: Babel project research at cued","author":"gales","year":"2014","journal-title":"Fourth International Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU-2014)"},{"key":"ref5","first-page":"2625","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Data-driven pronunciation modeling of swiss german di-alectal speech for automatic speech recognition","author":"stadtschnitzer","year":"0","journal-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)"},{"key":"ref7","article-title":"Swiss parliaments corpus, an automatically aligned swiss german speech to standard german text corpus","volume":"abs 2010 2810","author":"pl\u00fcss","year":"2020","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref9","article-title":"Swissdial: Parallel multidialectal cor-pus of spoken swiss german","author":"dogan-sch\u00f6nberger","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref1","volume":"1","author":"dieth","year":"1986","journal-title":"Schwyzertütschi Dialäktschrift Dieth-Schreibung"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.224"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref23","first-page":"369","article-title":"Connectionist temporal classi-fication: labelling unsegmented sequence data with re-current neural networks","author":"graves","year":"0","journal-title":"Proceedings of the 23rd in-ternational conference on Machine learning"},{"key":"ref26","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"2896","article-title":"Modeling Dialectal Variation for Swiss Ger-man Automatic Speech Recognition","author":"khosravani","year":"0","journal-title":"Proc INTERSPEECH 2021"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","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\/09688249.pdf?arnumber=9688249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:44Z","timestamp":1652733704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688249\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688249","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}