{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:22:53Z","timestamp":1777422173458,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888086","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper"],"prefix":"10.1109","author":[{"given":"Jiaming","family":"Zhou","sequence":"first","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Shiwan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Jiabei","family":"He","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Wenjia","family":"Zeng","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd."}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd."}]},{"given":"Haoqin","family":"Sun","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Aobo","family":"Kong","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447149"},{"key":"ref6","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref7","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"issue":"97","key":"ref8","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1360"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832235"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095177"},{"key":"ref12","article-title":"Childmandarin: A comprehensive mandarin speech dataset for young children aged 3-5","author":"Zhou","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-918"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2022.021755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3301230"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.319"},{"key":"ref17","article-title":"Accented speech recognition: Benchmarking, pre-training, and diverse data","author":"Aks\u00ebnova","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.564"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11031"},{"key":"ref22","article-title":"An exploration of in-context learning for speech language model","author":"Hsu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref24","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446502"},{"key":"ref27","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"ICLR","author":"Khandelwal"},{"key":"ref28","article-title":"Nearest neighbor machine translation","volume-title":"ICLR","author":"Khandelwal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref30","first-page":"38325","article-title":"Why do nearest neighbor language models work?","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447075"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref34","article-title":"Kespeech: An open source speech dataset of mandarin and its eight subdialects","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Tang"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888086.pdf?arnumber=10888086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:02Z","timestamp":1774416242000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888086","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}