{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:42Z","timestamp":1775230062121,"version":"3.50.1"},"reference-count":49,"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\/icassp49357.2023.10095326","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":23,"title":["Improving Massively Multilingual ASR with Auxiliary CTC Objectives"],"prefix":"10.1109","author":[{"given":"William","family":"Chen","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumi","family":"Maiti","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2426","article-title":"Unsupervised Cross-Lingual Representation Learning for Speech Recognition","author":"conneau","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"8249","article-title":"Universal phone recognition with a multilingual allophone system","author":"li","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1944"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref17","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED","author":"gales","year":"2014","journal-title":"Proc 4th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2014)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747905"},{"key":"ref19","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"babu","year":"2021"},{"key":"ref18","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"English in Proceedings of the Twelfth Language Resources and Evaluation Conference"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref45","article-title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech asr","author":"chen","year":"2022"},{"key":"ref48","article-title":"Robust speech recognition via large-scale weak supervision","author":"radford","year":"0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref42","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10712"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747671"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-152"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref35","article-title":"CTC alignments improve autoregressive translation","author":"yan","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747537"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref31","article-title":"Improving ctc-based asr models with gated interlayer collaboration","author":"yang","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref32","article-title":"Multi-sequence intermediate conditioning for ctc-based asr","author":"fujita","year":"2022"},{"key":"ref2","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"bapna","year":"2022"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639530"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref22","author":"lewis","year":"2009","journal-title":"Ethnologue Languages of the World"},{"key":"ref21","article-title":"Fleurs: Few-shot learning evaluation of universal representations of speech","author":"conneau","year":"2022"},{"key":"ref28","article-title":"Intermediate-layer output regularization for attention-based speech recognition with shared decoder","author":"zhang","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746580"}],"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\/10095326.pdf?arnumber=10095326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:57:03Z","timestamp":1699883823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095326","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}