{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:23Z","timestamp":1776889043704,"version":"3.51.2"},"reference-count":56,"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\/slt61566.2024.10832146","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"147-154","source":"Crossref","is-referenced-by-count":8,"title":["Bestow: Efficient and Streamable Speech Language Model with The Best of Two Worlds in GPT and T5"],"prefix":"10.1109","author":[{"given":"Zhehuai","family":"Chen","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oleksii","family":"Hrinchuk","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna C.","family":"Puvvada","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nithin Rao","family":"Koluguri","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"\u017belasko","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv:2312.11805"},{"key":"ref3","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref7","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint arXiv:2310.13289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref9","article-title":"Prompting large language models with speech recognition abilities","author":"Fathullah","year":"2023","journal-title":"arXiv:2307.11795"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref11","article-title":"Qwen technical report","volume-title":"arXiv preprint arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref14","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref15","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1194"},{"key":"ref17","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref20","article-title":"Xtreme-s: Evaluating crosslingual speech representations","author":"Conneau","year":"2022","journal-title":"arXiv preprint arXiv:2203.10752"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref22","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref23","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024","journal-title":"arXiv preprint arXiv:2402.01831"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"issue":"140","key":"ref25","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445874"},{"key":"ref27","article-title":"m^2 ugen: Multi-modal music understanding and generation with the power of large language models","author":"Hussain","year":"2023","journal-title":"arXiv preprint arXiv:2311.11255"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref29","article-title":"Stateful fastconformer with cache-based inference for streaming automatic speech recognition","volume-title":"arXiv preprint arXiv:2312.17279","author":"Noroozi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref31","article-title":"Simulmt to simulst: Adapting simultaneous text translation to end-toend simultaneous speech translation","author":"Ma","year":"2020","journal-title":"arXiv preprint arXiv:2011.02048"},{"key":"ref32","article-title":"Efficient monotonic multihead attention","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2312.04515"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.65"},{"key":"ref34","article-title":"Speech reallm-real-time streaming speech recognition with multimodal llms by teaching the flow of time","author":"Seide","year":"2024","journal-title":"arXiv preprint arXiv:2406.09569"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-705"},{"key":"ref36","article-title":"Simul-llm: A framework for exploring highquality simultaneous translation with large language models","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2312.04691"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.27"},{"key":"ref38","article-title":"Simultaneous machine translation with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2309.06706"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1575"},{"key":"ref45","article-title":"Dynamic-superb leaderboard"},{"key":"ref46","article-title":"Dynamic-superb: Towards a dynamic, collaborative, and comprehensive instruction-tuning benchmark for speech","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2309.09510"},{"key":"ref47","article-title":"Canary-1b model","year":"2024"},{"key":"ref48","article-title":"Ms marco: A human generated machine reading comprehension dataset","author":"Bajaj","year":"2016","journal-title":"arXiv preprint arXiv:1611.09268"},{"key":"ref49","article-title":"Overgeneration cannot be rewarded: Length-adaptive average lagging for simultaneous speech translation","author":"Papi","year":"2022","journal-title":"arXiv preprint arXiv:2206.05807"},{"key":"ref50","article-title":"NeMo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv:1909.09577"},{"key":"ref51","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024"},{"key":"ref52","first-page":"76697673","article-title":"Libri-light: A benchmark for asr with limited or no supervision","author":"Kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref53","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020","journal-title":"LREC"},{"key":"ref54","article-title":"Open automatic speech recognition leaderboard","author":"Srivastav","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"}],"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\/10832146.pdf?arnumber=10832146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:26Z","timestamp":1737398366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832146","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}