{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:20:05Z","timestamp":1776385205036,"version":"3.51.2"},"reference-count":38,"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\/icassp49357.2023.10094667","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities"],"prefix":"10.1109","author":[{"given":"Andros","family":"Tjandra","sequence":"first","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nayan","family":"Singhal","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelrahman","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duc","family":"Le","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael L.","family":"Seltzer","sequence":"additional","affiliation":[{"name":"Meta,AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"5135","article-title":"Scaling ASR Improves Zero and Few Shot Learning","author":"xiao","year":"2022","journal-title":"Proc Interspeech 2022"},{"key":"ref35","article-title":"Training deep nets with sublinear memory cost","author":"chen","year":"2016","journal-title":"arXiv preprint arXiv 1604 06174"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref34","article-title":"Fairscale: A general purpose modular pytorch library for high performance and large scale training","author":"authors","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref36","article-title":"Mixed precision training","author":"micikevicius","year":"2017","journal-title":"arXiv preprint arXiv 1710 03740"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1006\/csla.2001.0184","article-title":"Weighted finite-state transducers in speech recognition","volume":"16","author":"mohri","year":"2002","journal-title":"Comput Speech Lang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2440"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref1","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc of ICML Representation Learning Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref24","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016","journal-title":"arXiv Learning"},{"key":"ref23","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref26","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","article-title":"Learning asr pathways: A sparse multilingual asr model","author":"yang","year":"2022","journal-title":"arXiv preprint arXiv 2209 05735"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"arXiv preprint arXiv 1211 3711"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1298"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2277"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref3","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref5","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"}],"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\/10094667.pdf?arnumber=10094667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:05:06Z","timestamp":1700507106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094667","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}