{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:38Z","timestamp":1775199638801,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434619","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["ZO-ASR: Zeroth-Order Fine-Tuning of Speech Foundation Models without Back-Propagation"],"prefix":"10.1109","author":[{"given":"Yuezhang","family":"Peng","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence"}]},{"given":"Yuxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence"}]},{"given":"Yao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Aviation Electric Co., Ltd"}]},{"given":"Sheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence"}]},{"given":"Fei","family":"Wen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Information Science and Electronic Engineering\/School of Integrated Circuits"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,X-LANCE Lab, School of Computer Science, MoE Key Lab of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv:2001.08361"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML. PMLR","author":"Radford"},{"key":"ref5","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref8","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref10","first-page":"53038","article-title":"Fine-tuning language models with just forward passes","volume-title":"Proc. NeurIPS","volume":"36","author":"Malladi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-600"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-892"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1505"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1282"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1116"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268911"},{"key":"ref22","article-title":"Enhancing zerothorder fine-tuning for language models with low-rank structures","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2410.07698"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2409256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref25","first-page":"3731","article-title":"Zeroth-order stochastic variance reduction for nonconvex optimization","volume-title":"Proc. NeurIPS","volume":"31","author":"Liu"},{"key":"ref26","article-title":"Galore: Memory-efficient LLM training by gradient low-rank projection","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv:2403.03507"},{"key":"ref27","article-title":"FLORA: Low-rank adapters are secretly gradient compressors","author":"Hao","year":"2024","journal-title":"arXiv preprint arXiv:2402.03293"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"issue":"2","key":"ref29","first-page":"107","article-title":"The commitmentbank: Investigating projection in naturally occurring discourse","volume-title":"proceedings of Sinn und Bedeutung","volume":"23","author":"De Marneffe"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"ref31","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref35","article-title":"Variance-reduced zeroth-order methods for fine-tuning language models","volume-title":"Proc. ICML","author":"Gautam"},{"key":"ref36","first-page":"7202","article-title":"ZO-AdaMM: Zeroth-order adaptive momentum method for black-box optimization","volume-title":"Proc. NeurIPS","volume":"32","author":"Chen"},{"key":"ref37","article-title":"Secondorder fine-tuning without pain for 11 ms: A hessian informed zerothorder optimizer","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv:2402.15173"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref39","first-page":"62557","article-title":"Sglang: Efficient execution of structured language model programs","volume-title":"Proc. NeurIPS","volume":"37","author":"Zheng"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434619.pdf?arnumber=11434619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:16Z","timestamp":1775192236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434619","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}