{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:59:08Z","timestamp":1777568348775,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888774","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Scaling A Simple Approach to Zero-Shot Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Zhao","sequence":"first","affiliation":[{"name":"Monash University,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineel","family":"Pratap","sequence":"additional","affiliation":[{"name":"Meta Fair,Menlo Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[{"name":"Meta Fair,Menlo Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495646"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1163\/_afco_asc_441"},{"key":"ref6","article-title":"Representation learning with contrastive predictive coding","volume-title":"Proc. of NeurIPS","author":"van den Oord"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NeurIPS","author":"Baevski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","author":"Zhang","year":"2023","journal-title":"Google usm: Scaling automatic speech recognition beyond 100 languages"},{"key":"ref11","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2024","journal-title":"JMLR"},{"key":"ref12","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. of ICML","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2068"},{"key":"ref15","article-title":"Unsupervised speech recognition","volume-title":"Proc. of NeurIPS","author":"Baevski"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10712"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.166"},{"key":"ref19","author":"Mortensen","year":"2020","journal-title":"Allovera: A multilingual allophone database"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref22","article-title":"The conversion of scripts, its nature, history, and utilization","author":"Wellisch","year":"1978"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref24","article-title":"Panlex: Building a resource for panlingual lexical translation","volume-title":"Proc. of LREC","author":"Kamholz"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref26","article-title":"The cr\u00fabad\u00e1n project: Corpus building for under-resourced languages","volume-title":"Proc. of WAC","author":"Scannell"},{"key":"ref27","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. of LREC","author":"Ardila"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref29","article-title":"Flashlight: Enabling innovation in tools for machine learning","volume-title":"Proc. of ICML","author":"Kahn"},{"key":"ref30","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proc. of WMT","author":"Heafield"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888774.pdf?arnumber=10888774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:49Z","timestamp":1774416109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888774","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}