{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:24Z","timestamp":1775230104169,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446502","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13421-13425","source":"Crossref","is-referenced-by-count":24,"title":["Can Whisper Perform Speech-Based In-Context Learning?"],"prefix":"10.1109","author":[{"given":"Siyin","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Chao-Han","family":"Yang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,USA"}]},{"given":"Ji","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.193"},{"key":"ref6","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. NeurIPS","author":"Tsimpoukelli"},{"key":"ref7","article-title":"Calibrate before use: Improving few-shot performance of language models","volume-title":"Proc. ICML","author":"Zhao"},{"key":"ref8","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. ICLR","author":"Wei"},{"key":"ref9","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref10","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8181-6_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1799"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288905"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.03.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1809"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462557"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1864"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178819"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1606"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.42"},{"key":"ref31","article-title":"Quantifying bias in automatic speech recognition","author":"Feng","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2528"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1044"},{"key":"ref34","article-title":"Introduction to RASC863","year":"2004"},{"key":"ref35","article-title":"An explanation of in-context learning as implicit Bayesian inference","volume-title":"Proc. ICLR","author":"Xie"},{"key":"ref36","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"Proc. ICLR","author":"Khandelwal"},{"key":"ref37","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446502.pdf?arnumber=10446502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:19:33Z","timestamp":1722575973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446502","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}