{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:17:16Z","timestamp":1780672636603,"version":"3.54.1"},"reference-count":25,"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\/icassp48485.2024.10447605","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13351-13355","source":"Crossref","is-referenced-by-count":94,"title":["Prompting Large Language Models with Speech Recognition Abilities"],"prefix":"10.1109","author":[{"given":"Yassir","family":"Fathullah","sequence":"first","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junteng","family":"Jia","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Shangguan","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxi","family":"Guo","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Mahadeokar","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Fuegen","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Seltzer","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Le Scao","year":"2022"},{"key":"ref5","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref6","article-title":"Scaling vision transformers to 22 billion parameters","author":"Dehghani","year":"2023"},{"key":"ref7","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref8","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref9","article-title":"Listen, think, and understand","author":"Gong","year":"2023"},{"key":"ref10","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Houlsby"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref18","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021"},{"key":"ref19","article-title":"Unsupervised crosslingual representation learning for speech recognition","author":"Conneau","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref21","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Baevski"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref23","article-title":"Self-supervised learning with randomprojection quantizer for speech recognition","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Chiu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095651"}],"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\/10447605.pdf?arnumber=10447605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:52:13Z","timestamp":1722577933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447605","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}