{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:10Z","timestamp":1776890050167,"version":"3.51.2"},"reference-count":35,"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\/icassp49660.2025.10890853","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Streaming LLM for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Junteng","family":"Jia","sequence":"first","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gil","family":"Keren","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Seide","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Mahadeokar","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref2","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref3","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref5","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"issue":"97","key":"ref9","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003972"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-571"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref15","article-title":"Monotonic chunkwise attention","author":"Chiu","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3031480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022818"},{"key":"ref19","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446035"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref23","article-title":"Speechprompt v2: Prompt tuning for speech classification tasks","author":"Chang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref25","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1962"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref28","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023"},{"key":"ref29","article-title":"Towards efficient generative large language model serving: A survey from algorithms to systems","author":"Miao","year":"2023"},{"key":"ref30","article-title":"Leave no context behind: Efficient infinite context transformers with infiniattention","author":"Munkhdalai","year":"2024"},{"key":"ref31","article-title":"Advancing transformer architecture in long-context large language models: A comprehensive survey","author":"Huang","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/634"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref34","article-title":"Megalodon: Efficient llm pretraining and inference with unlimited context length","author":"Ma","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-705"}],"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\/10890853.pdf?arnumber=10890853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:36Z","timestamp":1774416156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890853","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}