{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:16Z","timestamp":1775229856421,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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 J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3588378","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:47:54Z","timestamp":1752169674000},"page":"1329-1337","source":"Crossref","is-referenced-by-count":4,"title":["AlignFormer: Modality Matching Can Achieve Better Zero-Shot Instruction-Following Speech-LLM"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5021-2747","authenticated-orcid":false,"given":"Ruchao","family":"Fan","sequence":"first","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Bo","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Yuxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2599-6752","authenticated-orcid":false,"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 33, Annu. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref2","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref5","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref6","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rafailov","year":"2024"},{"key":"ref7","article-title":"Moshi: A speech-text foundation model for real-time dialogue","author":"Dfossez","year":"2024"},{"key":"ref8","article-title":"Freeze-omni: A smart and low latency speech-to-speech dialogue model with frozen LLM","author":"Wang","year":"2024"},{"key":"ref9","article-title":"Mini-omni2: Towards open-source gpt-4o with vision, speech and duplex capabilities","author":"Xie","year":"2024"},{"key":"ref10","article-title":"SALMONN-omni: A codec-free LLM for full-duplex speech understanding and generation","author":"Yu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref12","article-title":"LauraGPT: Listen, attend, understand, and regenerate audio with GPT","author":"Du","year":"2023"},{"key":"ref13","article-title":"An embarrassingly simple approach for LLM with strong ASR capacity","author":"Ma","year":"2024"},{"key":"ref14","article-title":"SALMONN: Towards generic hearing abilities for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Tang","year":"2024"},{"key":"ref15","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1346"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref19","article-title":"Speechverse: A large-scale generalizable audio language model","author":"Das","year":"2024"},{"key":"ref20","article-title":"High fidelity neural audio compression","volume":"2023","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref21","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2024"},{"key":"ref22","article-title":"Seed-ASR: Understanding diverse speech and contexts with LLM-based speech recognition","author":"Bai","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"ref25","article-title":"BLSP: Bootstrapping language-speech pre-training via behavior alignment of continuation writing","author":"Wang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889444"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-166"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.354"},{"key":"ref29","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref30","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras","author":"Abouelenin","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413429"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3365036"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/slt61566.2024.10832212"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref38","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-592"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888940"},{"key":"ref42","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3263789"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11077996.pdf?arnumber=11077996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T18:37:32Z","timestamp":1767292652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11077996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":46,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3588378","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}