It's Never Too Late : Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

Chen, ChenLi, RuizheHu, YuchenSiniscalchi, Sabato MarcoChen, Pin-YuChng, EnsiongYang, Chao-Han Huck2024-02-272024-02-272024-05-06Chen, C, Li, R, Hu, Y, Siniscalchi, S M, Chen, P-Y, Chng, E & Yang, C-H H 2024, It's Never Too Late : Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition. in ICLR 2024. ICLR 2024 , Vienna, Austria, 7/05/24. https://doi.org/10.48550/arXiv.2402.05457conferenceArXiv: http://arxiv.org/abs/2402.05457v1ORCID: /0000-0003-2512-845X/work/154626426https://hdl.handle.net/2164/22863Accepted to ICLR 2024, 17 pages. This work will be open sourced under MIT license17605887engcs.CLcs.AIcs.MMcs.SDeess.ASQA75 Electronic computers. Computer scienceQA75It's Never Too Late : Fusing Acoustic Information into Large Language Models for Automatic Speech RecognitionConference item10.48550/arXiv.2402.05457https://openreview.net/group?id=ICLR.cc/2024/Conference#tab-accept-oralfile:///C:/Users/s01gv9/Downloads/3711_it_s_never_too_late_fusing_aco.pdf