{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:35:11Z","timestamp":1776890111059,"version":"3.51.2"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887683","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Target Speaker ASR with Whisper"],"prefix":"10.1109","author":[{"given":"Alexander","family":"Polok","sequence":"first","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Dominik","family":"Klement","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Matthew","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,United States of America"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,United States of America"}]},{"given":"Jan","family":"\u010cernock\u00fd","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]},{"given":"Luk\u00e1\u0161","family":"Burget","sequence":"additional","affiliation":[{"name":"Brno University of Technology,Brno,Czech Republic"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"issue":"97","key":"ref3","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":"ref4","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3318398"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163922"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"},{"key":"ref23","article-title":"The AMI meeting corpus","author":"Mccowan","year":"2005","journal-title":"Int\u2019l. Conf. on Methods and Techniques in Behavioral Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746465"},{"key":"ref25","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref26","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-6"},{"key":"ref28","article-title":"Dicow: Diarization-conditioned whisper for target speaker automatic speech recognition","author":"Polok","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-7"},{"key":"ref30","first-page":"518","article-title":"Joint CTC\/attention decoding for end-to-end speech recognition","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Hori"},{"key":"ref31","article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889475"}],"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\/10887683.pdf?arnumber=10887683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:47Z","timestamp":1774416407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887683","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}