{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T12:17:41Z","timestamp":1783772261022,"version":"3.55.0"},"reference-count":38,"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\/slt54892.2023.10023141","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"798-805","source":"Crossref","is-referenced-by-count":155,"title":["FLEURS: FEW-Shot Learning Evaluation of Universal Representations of Speech"],"prefix":"10.1109","author":[{"given":"Alexis","family":"Conneau","sequence":"first","affiliation":[{"name":"Meta AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simran","family":"Khanuja","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vera","family":"Axelrod","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Riesa","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clara","family":"Rivera","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Bapna","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref2","article-title":"mSLAM: Massively multilin-gual joint pre-training for speech and text","volume":"abs\/2202.01374","author":"Bapna","year":"2022","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NeurIPS","author":"Baevski","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414641"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref16","article-title":"Common Voice: A massively-multilingual speech cor-pus","volume-title":"Proc. of LREC","author":"Ardila","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref21","article-title":"Cvss corpus and massively multi-lingual speech-to-speech translation","author":"Jia","year":"2022","journal-title":"ar Xiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383459"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683536"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39886-8_29"},{"key":"ref26","article-title":"mT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639699"},{"key":"ref31","article-title":"Speech recognition and information retrieval: Exper-iments in retrieving spoken documents","volume-title":"Proceedings of the DARPA speech recognition workshop","volume":"97","author":"Witbrock","year":"1997"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"ref35","article-title":"Multimodal and multilingual embeddings for large-scale speech mining","volume":"34","author":"Duquenne","year":"2021","journal-title":"Advances in Neural In-formation Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/746"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/NCVPRIPG.2015.7490020"}],"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\/10023141.pdf?arnumber=10023141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:27:18Z","timestamp":1707812838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023141","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}