{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:36:19Z","timestamp":1787758579500,"version":"build-2784847793"},"reference-count":53,"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\/slt54892.2023.10022724","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"205-212","source":"Crossref","is-referenced-by-count":33,"title":["How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted Asr? an Extensive Benchmark on Air Traffic Control Communications"],"prefix":"10.1109","author":[{"given":"Juan","family":"Zuluaga-Gomez","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amrutha","family":"Prasad","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iuliia","family":"Nigmatulina","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyyed Saeed","family":"Sarfjoo","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petr","family":"Motlicek","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Martigny,Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Kleinert","sequence":"additional","affiliation":[{"name":"Institute of Flight Guidance,German Aerospace Center (DLR),Braunschweig,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hartmut","family":"Helmke","sequence":"additional","affiliation":[{"name":"Institute of Flight Guidance,German Aerospace Center (DLR),Braunschweig,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Ohneiser","sequence":"additional","affiliation":[{"name":"Institute of Flight Guidance,German Aerospace Center (DLR),Braunschweig,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingran","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref3","article-title":"vq-wav2vec: Self-supervised learning of discrete speech represen-tations","author":"Baevski","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"12449","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 Infor-mation Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref6","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02075-7"},{"key":"ref10","article-title":"X1s-r: Self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","year":"2020","journal-title":"Icao phraseology reference guide"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-935"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1373"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747897"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-353"},{"key":"ref17","article-title":"ASR4REAL: An extended benchmark for speech models","author":"Riviere","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2016.7778024"},{"key":"ref19","article-title":"Increasing atm efficiency with assistant based speech recognition","volume-title":"Proc. of the 13th USA\/Europe Air Traffic Man-agement Research and Development Seminar","author":"Helmke"},{"issue":"1","key":"ref20","first-page":"8","article-title":"Au-tomatic processing pipeline for collecting and annotating air-traffic voice communication data","volume-title":"Engineering Proceedings","volume":"13","author":"Kocour"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2173"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/proceedings2020059014"},{"key":"ref23","article-title":"Grammar Based Identification Of Speaker Role For Improving ATCO And Pilot ASR","author":"Prasad","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1446"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2018.8569879"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace8030065"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-86"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1619"},{"key":"ref31","article-title":"Improving callsign recognition with air-surveillance data in air-traffic communication","author":"Nigmatulina","year":"2021","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746563"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414741"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1683"},{"key":"ref40","author":"Godfrey","year":"1994","journal-title":"The Air Traffic Control Corpus (ATC0)-LDC94S14A"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-019-09449-5"},{"key":"ref42","article-title":"The atcosim corpus of non-prompted clean air traffic control speech","author":"Hofbauer","year":"2008","journal-title":"LREC"},{"key":"ref43","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE workshop on automatic speech recognition and understanding. IEEE Signal Processing Soci-ety","volume":"2011","author":"Povey"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"issue":"1","key":"ref47","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref48","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Rep-resentations","author":"Loshchilov"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747323"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"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\/10022724.pdf?arnumber=10022724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:55:43Z","timestamp":1710370543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022724","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}