{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T18:05:11Z","timestamp":1780941911870,"version":"3.54.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447553","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13521-13525","source":"Crossref","is-referenced-by-count":34,"title":["SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation"],"prefix":"10.1109","author":[{"given":"Zhehuai","family":"Chen","sequence":"first","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":"Andrei","family":"Andrusenko","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 C.","family":"Puvvada","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhankar","family":"Ghosh","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"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","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref2","volume-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref4","article-title":"X-llm: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref8","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref9","article-title":"Listen, think, and understand","author":"Gong","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448204"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref12","article-title":"Prompting large language models with speech recognition abilities","author":"Fathullah","year":"2023"},{"key":"ref13","article-title":"Speechto-text adapter and speech-to-entity retriever augmented llms for speech understanding","author":"Wang","year":"2023"},{"key":"ref14","article-title":"Megatron-lm: Training multibillion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref15","article-title":"NeMo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1440"},{"key":"ref17","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3379877"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref28","article-title":"Finetuned language models are zero-shot learners","volume-title":"ICLR","author":"Wei"},{"key":"ref29","article-title":"A survey for incontext learning","author":"Dong","year":"2022"},{"key":"ref30","article-title":"The stack: 3 tb of permissively licensed source code","author":"Kocetkov","year":"2022","journal-title":"Preprint"},{"key":"ref31","article-title":"The curious case of neural text degeneration","author":"Holtzman","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3036335"},{"key":"ref36","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref37","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6318"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447553.pdf?arnumber=10447553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:34:14Z","timestamp":1722573254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447553","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}