{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:30Z","timestamp":1775230110902,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832175","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"255-262","source":"Crossref","is-referenced-by-count":3,"title":["Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation"],"prefix":"10.1109","author":[{"given":"Nithin Rao","family":"Koluguri","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Travis","family":"Bartley","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hainan","family":"Xu","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oleksii","family":"Hrinchuk","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Kucsko","sequence":"additional","affiliation":[{"name":"Suno Inc,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref2","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv:2010.10504"},{"key":"ref3","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687976"},{"key":"ref6","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeuRIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref8","article-title":"Training-free long-context scaling of large language models","author":"An","year":"2024"},{"key":"ref9","article-title":"Investigating end-to-end asr architectures for long form audio transcription","author":"Koluguri","year":"2023","journal-title":"arXiv:2309.09950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1915"},{"key":"ref11","article-title":"Earnings-22: A practical benchmark for accents in the wild","author":"Rio","year":"2022","journal-title":"arXiv preprint arXiv:2203.15591"},{"key":"ref12","first-page":"2012","article-title":"Must-c: a multilingual speech translation corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Di Gangi"},{"key":"ref13","article-title":"Efficient sequence transduction by jointly predicting tokens and durations","author":"Xu","year":"2023","journal-title":"arXiv:2304.06795"},{"key":"ref14","article-title":"Stateful fastconformer with cache-based inference for streaming automatic speech recognition","volume-title":"arXiv:2312.17279","author":"Noroozi"},{"key":"ref15","article-title":"4 d asr: Joint beam search integrating ctc, attention, transducer, and mask predict decoders","author":"Sudo","year":"2024","journal-title":"arXiv preprint arXiv:2406.02950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389666"},{"key":"ref17","article-title":"Updated corpora and benchmarks for long-form speech recognition","author":"Fox","year":"2023","journal-title":"arXiv:2309.15013"},{"key":"ref18","article-title":"Fisher english training speech part 1 transcripts","author":"Cieri","year":"2004","journal-title":"Philadelphia: Linguistic Data Consortium"},{"key":"ref19","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv:1912.06670"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref21","article-title":"Spontaneous speech elicitation for large speech corpus in multilingual singapore","author":"Tan"},{"key":"ref22","article-title":"Spgispeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","author":"Patrick","year":"2021","journal-title":"arXiv:2104.02014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref25","article-title":"The ami meeting corpus","volume-title":"Int\u2019l. Conf. on Methods and Techniques in Behavioral Research","volume":"01","author":"Mccowan"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref29","article-title":"Ctc alignments improve autoregressive translation","author":"Yan","year":"2022","journal-title":"arXiv:2210.05200"},{"key":"ref30","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832175.pdf?arnumber=10832175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:10Z","timestamp":1737100210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832175","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}