{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:42Z","timestamp":1783439922123,"version":"3.54.6"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3419719","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T21:10:46Z","timestamp":1719522646000},"page":"1740-1744","source":"Crossref","is-referenced-by-count":8,"title":["Tuning Large Language Model for Speech Recognition With Mixed-Scale Re-Tokenization"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0520-4331","authenticated-orcid":false,"given":"Yukun","family":"Ma","sequence":"first","affiliation":[{"name":"Speech Lab, Institute for Intelligent Computing, Alibaba Group, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2162-4344","authenticated-orcid":false,"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Speech Lab, Institute for Intelligent Computing, Alibaba Group, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Speech Lab, Institute for Intelligent Computing, Alibaba Group, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-1968","authenticated-orcid":false,"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech Lab, Institute for Intelligent Computing, Alibaba Group, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[{"name":"Speech Lab, Institute for Intelligent Computing, Alibaba Group, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Wei","year":"2022"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref4","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Tang","year":"2024"},{"key":"ref5","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref6","article-title":"LMS with a voice: Spoken language modeling beyond speech tokens","author":"Nachmani","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref9","first-page":"11","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"Assoc. Comput. Linguistics"},{"key":"ref10","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023"},{"key":"ref11","article-title":"Wavjourney: Compositional audio creation with large language models","author":"Liu","year":"2023"},{"key":"ref12","article-title":"LLASM: Large language and speech model","author":"Shu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200909"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref15","article-title":"Speechtokenizer: Unified speech tokenizer for speech large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447296"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2359"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref24","article-title":"Its never too late: Fusing acoustic information into large language models for automatic speech recognition","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-981"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref27","article-title":"Charformer: Fast character transformers via gradient-based subword tokenization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tay","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.207"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00486"},{"key":"ref31","article-title":"Unified language-vision pretraining in LLM with dynamic discrete visual tokenization","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Jin","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00091"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2021"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10574347.pdf?arnumber=10574347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T04:13:44Z","timestamp":1720412024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10574347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3419719","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}