{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:14:07Z","timestamp":1792599247910,"version":"4.5.0"},"reference-count":27,"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\/icassp49660.2025.10890201","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Beyond Speaker Identity: Text Guided Target Speech Extraction"],"prefix":"10.1109","author":[{"given":"Mingyue","family":"Huo","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Jain","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong Phuoc","family":"Huynh","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanjie","family":"Kong","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhu","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vimal","family":"Bhat","sequence":"additional","affiliation":[{"name":"Amazon Prime Video"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref7","article-title":"CLIPSep: Learning text-queried sound separation with noisy unlabeled videos","author":"Dong","year":"2023","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095266"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref11","article-title":"Typing to listen at the cocktail party: Text-guided target speaker extraction","author":"Hao","year":"2023"},{"key":"ref12","article-title":"Target speech diarization with multimodal prompts","author":"Jiang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref14","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445879"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683874"},{"key":"ref17","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref22","article-title":"Semi-supervised time domain target speaker extraction with attention","volume-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29846"}],"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\/10890201.pdf?arnumber=10890201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:58Z","timestamp":1774416298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890201","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}