{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:00:25Z","timestamp":1783008025697,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389701","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":86,"title":["Fast Conformer With Linearly Scalable Attention For Efficient Speech Recognition"],"prefix":"10.1109","author":[{"given":"Dima","family":"Rekesh","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nithin Rao","family":"Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Kriman","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somshubra","family":"Majumdar","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vahid","family":"Noroozi","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleksii","family":"Hrinchuk","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishna","family":"Puvvada","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of California,Department of Computer Science,Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref4","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv:2010.10504"},{"key":"ref5","article-title":"Longformer: The long-document Transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref6","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref8","article-title":"Squeezeformer: An efficient Transformer for automatic speech recognition","volume-title":"NeurIPS","author":"Kim"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10095430","article-title":"Uconv-conformer: High reduction of input sequence length for end-to-end speech recognition","volume-title":"ICASSP","author":"Andrusenko"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","article-title":"Sequence transduction with recurrent neural networks","volume-title":"ICML","author":"Graves"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref17","volume-title":"Mozilla: A journey to less than 10% word error rate"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref19","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.10"},{"key":"ref21","article-title":"NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21","author":"Subramanian","year":"2021","journal-title":"arXiv:2111.08634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref27","article-title":"A fine-tuned Wav2vec 2.0\/Hu-BERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021","journal-title":"arXiv:2111.02735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1915"},{"key":"ref30","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref31","volume-title":"Open automatic speech recognition leaderboard","author":"Srivastav","year":"2023"},{"key":"ref32","volume-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref33","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389701.pdf?arnumber=10389701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:12Z","timestamp":1706027772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389701","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}