{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:02:39Z","timestamp":1776880959312,"version":"3.51.2"},"reference-count":40,"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\/icassp49660.2025.10888110","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models"],"prefix":"10.1109","author":[{"given":"Shashi","family":"Kumar","sequence":"first","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikanth","family":"Madikeri","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Zuluaga-Gomez","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esa\u00fa","family":"Villatoro-Tello","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iuliia","family":"Thorbecke","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petr","family":"Motlicek","sequence":"additional","affiliation":[{"name":"Idiap Research Institute,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjunath K","family":"E","sequence":"additional","affiliation":[{"name":"Uniphore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aravind","family":"Ganapathiraju","sequence":"additional","affiliation":[{"name":"Uniphore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1611"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10340"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446861"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref15","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054309"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2018.8569879"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3246"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21327"},{"key":"ref23","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094588"},{"key":"ref25","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023"},{"key":"ref26","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"International Conference on Machine Learning","author":"Chiu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref30","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1683","article-title":"Comparing ctc and lfmmi for out-of-domain adaptation of wav2vec 2.0 acoustic model","volume-title":"Proceedings of Interspeech","author":"Vyas"},{"key":"ref33","first-page":"17 283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.222"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref37","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1188"}],"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\/10888110.pdf?arnumber=10888110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:52Z","timestamp":1774416052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888110","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}