{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:44Z","timestamp":1776889064885,"version":"3.51.2"},"reference-count":36,"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\/501100009036","name":"Strategic International Collaborative Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009036","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\/icassp49660.2025.10888410","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":6,"title":["SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Hernandez-Olivan","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Niizumi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naohiro","family":"Tawara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606779"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2210"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747835"},{"key":"ref9","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","volume":"202","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448315"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715391"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref24","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref29","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref30","article-title":"Noise files for the disco dataset","author":"Furnon","year":"2020"},{"key":"ref31","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","volume-title":"Proc. DCASE","author":"Mesaros"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969552"},{"key":"ref33","article-title":"The Salford BBC spatially-sampled binaural room impulse response dataset","author":"Satongar","year":"2015"},{"key":"ref34","article-title":"Iosr-surrey\/realroombrirs: Binaural impulse responses captured in real rooms","year":"2016"},{"key":"ref35","article-title":"Simulated room impulse responses","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"}],"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\/10888410.pdf?arnumber=10888410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:43Z","timestamp":1774416283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888410","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}