{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:45:07Z","timestamp":1776887107519,"version":"3.51.2"},"reference-count":28,"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"}],"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447492","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12516-12520","source":"Crossref","is-referenced-by-count":18,"title":["Extending Whisper with Prompt Tuning to Target-Speaker ASR"],"prefix":"10.1109","author":[{"given":"Hao","family":"Ma","sequence":"first","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"North Carolina State University,Department of Computer Science,North Carolina,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Shao","sequence":"additional","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Normal University,School of Journalism and Communication,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University,School of Information Science and Engineering,Qingdao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Int. Conf. Mach Learn. (ICML)","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952154"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095295"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"ref12","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Houlsby"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.421"},{"key":"ref17","article-title":"Speechprompt v2: Prompt tuning for speech classification tasks","author":"Chang","year":"2023"},{"key":"ref18","article-title":"Prompt tuning of deep neural networks for speaker-adaptive visual speech recognition","author":"Kim","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref20","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"CoRR"},{"key":"ref21","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Advances Neural Inf. Process. Systems (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref23","article-title":"LibriMix: An opensource dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"}],"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\/10447492.pdf?arnumber=10447492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:43:17Z","timestamp":1722577397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447492","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}