{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:38Z","timestamp":1774419818953,"version":"3.50.1"},"reference-count":37,"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\/icassp49660.2025.10888750","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":0,"title":["Collision-less and Balanced Sampling for Language-Queried Audio Source Separation"],"prefix":"10.1109","author":[{"given":"Binh Thien","family":"Nguyen","sequence":"first","affiliation":[{"name":"NTT Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiki","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Yasuda","sequence":"additional","affiliation":[{"name":"NTT Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Niizumi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noboru","family":"Harada","sequence":"additional","affiliation":[{"name":"NTT Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Universal source separation with weakly labelled data","author":"Kong","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446601"},{"key":"ref4","article-title":"Into the wild with audioscope: Unsupervised audio-visual separation of on-screen sounds","author":"Tzinis","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606779"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095266"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10894"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref15","article-title":"Clipsep: Learning text-queried sound separation with noisy unlabeled videos","author":"Dong","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682395"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389636"},{"key":"ref23","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.580"},{"key":"ref26","article-title":"k-means++: The advantages of careful seeding","author":"Arthur","year":"2006","journal-title":"Stanford, Tech. Rep"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref29","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref33","article-title":"Language-queried audio source separation enhanced by expanded language-audio contrastive loss","author":"Chung","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep"},{"key":"ref34","article-title":"Srpol submission to dcase 2024 challenge task 9: Modeling real and imaginary components, mixit and sdr based loss","author":"Romaniuk","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep"},{"key":"ref35","article-title":"Language-queried audio source separation via resunet with dprnn","author":"Yin","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep"},{"key":"ref36","article-title":"Language-queried audio source separation with gpt-based text augmentation and ideal ratio masking","author":"Xiao","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep"},{"key":"ref37","article-title":"Performance improvement of language-queried audio source separation based on caption augmentation from large language models for dcase challenge 2024 task 9","author":"Lee","year":"2024","journal-title":"DCASE2024 Challenge, Tech. Rep"}],"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\/10888750.pdf?arnumber=10888750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:52Z","timestamp":1774416292000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888750","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}