{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:42:56Z","timestamp":1767678176972,"version":"3.48.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"publisher","award":["NSTC 112-2221-E-001-009-MY3"],"award-info":[{"award-number":["NSTC 112-2221-E-001-009-MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2025.3649090","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:39:29Z","timestamp":1767033569000},"page":"662-678","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Attention Reprogramming for ASR: Bridging Discrete Speech Units and Pretrained Language Models"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5992-2846","authenticated-orcid":false,"given":"Pei-Jun","family":"Liao","sequence":"first","affiliation":[{"name":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Electrical Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Textless-lib: A library for textless spoken language processing","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol., Syst. Demonstrations","author":"Kharitonov"},{"key":"ref2","first-page":"1681","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1878"},{"article-title":"UTDUSS: UTokyo\u2013SaruLab system for Interspeech2024 speech processing using discrete speech unit challenge","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc. (Interspeech)","author":"Nakata","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054224"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096827"},{"key":"ref9","first-page":"27928","article-title":"Time-LLM: Time series forecasting by reprogramming large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Jin"},{"key":"ref10","article-title":"Deep time series models: A comprehensive survey and benchmark","author":"Wang","year":"2024","journal-title":"arXiv:2407.13278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref13","article-title":"DASB\u2013discrete audio and speech benchmark","author":"Mousavi","year":"2024","journal-title":"arXiv:2406.14294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9052942"},{"key":"ref17","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Res. Eval. Conf. (LREC)","author":"Ardila"},{"key":"ref18","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","first-page":"2529","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096988"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2051"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095565"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-41"},{"key":"ref26","article-title":"Exploring SSL discrete tokens for multilingual ASR","author":"Cui","year":"2024","journal-title":"arXiv:2409.08805"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-310"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-2251"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1306"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832321"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889740"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10865"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1054"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icasspw65056.2025.11011236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(93)90090-R"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3516790"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/11550907_126"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IITSI.2010.74"},{"key":"ref45","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref46","article-title":"Joint beam search integrating CTC, attention, and transducer decoders","author":"Sudo","year":"2024","journal-title":"arXiv:2406.02950"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-849"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp63861.2024.10800400"},{"key":"ref49","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Syst. Demonstrations","author":"Wolf"},{"key":"ref50","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11316631.pdf?arnumber=11316631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:39:49Z","timestamp":1767677989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3649090","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2026]]}}}