{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:43:31Z","timestamp":1772041411344,"version":"3.50.1"},"reference-count":32,"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\/slt61566.2024.10832227","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"64-69","source":"Crossref","is-referenced-by-count":4,"title":["Effective Text Adaptation For LLM-Based ASR Through Soft Prompt Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Yingyi","family":"Ma","sequence":"first","affiliation":[{"name":"Meta AI,Menlo Park,CA,USA"}]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI,Menlo Park,CA,USA"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta AI,Menlo Park,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Palm 2 technical report","volume-title":"arXiv preprint arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref4","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv preprint arXiv:2306.09093"},{"key":"ref5","article-title":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023","journal-title":"arXiv preprint arXiv:2309.03905"},{"key":"ref6","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2309.05519"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref8","article-title":"On decoderonly architecture for speech-to-text and large language model integration","author":"Wu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1191"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746908"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414080"},{"key":"ref14","article-title":"Two-stage llm finetuning with less specialization and more generalization","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2211.00635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref17","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2402.05457"},{"key":"ref18","article-title":"Slam: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021","journal-title":"arXiv preprint arXiv:2110.10329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747555"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022774"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-906"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746475"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1656"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746217"},{"key":"ref30","article-title":"Differentiable prompt makes pre-trained language models better few-shot learners","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv:2108.13161"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"}],"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\/10832227.pdf?arnumber=10832227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:44:06Z","timestamp":1737099846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832227","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}