{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:48:49Z","timestamp":1780318129207,"version":"3.54.1"},"reference-count":45,"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\/icassp49660.2025.10887655","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":2,"title":["Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction"],"prefix":"10.1109","author":[{"given":"Minsu","family":"Kim","sequence":"first","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo","family":"Mira","sequence":"additional","affiliation":[{"name":"Imperial College,London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglie","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2015.7178061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053845"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746221"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2016.2647702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1400"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096390"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01024"},{"key":"ref15","article-title":"Typing to listen at the cocktail party: Text-guided target speaker extraction","author":"Hao","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10717"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2020.2980956"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11311"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01801"},{"key":"ref23","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref27","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054311"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref34","article-title":"Speechbrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref36","first-page":"986","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","volume-title":"Proc. of the International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li"},{"key":"ref37","article-title":"Spokenwoz: A large-scale speech-text benchmark for spoken task-oriented dialogue agents","volume":"36","author":"Si","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref42","article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref44","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref45","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"}],"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\/10887655.pdf?arnumber=10887655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:47Z","timestamp":1774416167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887655","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}