{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T14:40:59Z","timestamp":1770734459268,"version":"3.49.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"BK21 FOUR funded by the Ministry of Education of Korea and the National Research Foundation of Korea"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3656219","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:40:48Z","timestamp":1768941648000},"page":"17182-17195","source":"Crossref","is-referenced-by-count":0,"title":["CLAPMamba: CLAP-Guided Mamba for Language-Queried Target Sound Extraction"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6828-4355","authenticated-orcid":false,"given":"Jeong Yeol","family":"Yang","sequence":"first","affiliation":[{"name":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5308-6675","authenticated-orcid":false,"given":"Hyun Joon","family":"Park","sequence":"additional","affiliation":[{"name":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"}]},{"given":"Soyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0040-3542","authenticated-orcid":false,"given":"Sung Won","family":"Han","sequence":"additional","affiliation":[{"name":"School of Industrial and Management Engineering, Korea University, Seongbuk, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2024.109487"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref5","article-title":"Improved speech enhancement with the wave-U-Net","author":"Macartney","year":"2018","journal-title":"arXiv:1811.11307"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref8","article-title":"Decoupling magnitude and phase estimation with deep ResUNet for music source separation","author":"Kong","year":"2021","journal-title":"arXiv:2109.05418"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref10","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wisdom"},{"key":"ref11","article-title":"Universal source separation with weakly labelled data","author":"Kong","year":"2023","journal-title":"arXiv:2305.07447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447061"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2210"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref16","article-title":"CLIPSep: Learning text-queried sound separation with noisy unlabeled videos","author":"Dong","year":"2022","journal-title":"arXiv:2212.07065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248160"},{"key":"ref18","article-title":"OmniSep: Unified omni-modality sound separation with query-mixup","author":"Cheng","year":"2024","journal-title":"arXiv:2410.21269"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20366"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3520017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu"},{"key":"ref27","article-title":"An empirical study of mamba-based language models","author":"Waleffe","year":"2024","journal-title":"arXiv:2406.07887"},{"key":"ref28","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref29","article-title":"A survey on vision mamba: Models, applications and challenges","author":"Xu","year":"2024","journal-title":"arXiv:2404.18861"},{"key":"ref30","article-title":"Vivim: A video vision mamba for medical video segmentation","author":"Yang","year":"2024","journal-title":"arXiv:2401.14168"},{"key":"ref31","article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","author":"Chen","year":"2024","journal-title":"arXiv:2403.09626"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3418714"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832332"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889525"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888514"},{"key":"ref36","article-title":"SPMamba: State-space model is all you need in speech separation","author":"Li","year":"2024","journal-title":"arXiv:2404.02063"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888846"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832137"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3566210"},{"key":"ref40","article-title":"Audio mamba: Pretrained audio state space model for audio tagging","author":"Lin","year":"2024","journal-title":"arXiv:2405.13636"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-698"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1274"},{"key":"ref45","article-title":"SELD-mamba: Selective state-space model for sound event localization and detection with source distance estimation","author":"Mu","year":"2024","journal-title":"arXiv:2408.05057"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889391"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"ref49","article-title":"MaTrRec: Uniting mamba and transformer for sequential recommendation","author":"Zhang","year":"2024","journal-title":"arXiv:2407.19239"},{"key":"ref50","article-title":"A hybrid transformer-mamba network for single image deraining","author":"Sun","year":"2024","journal-title":"arXiv:2409.00410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3699757"},{"key":"ref52","article-title":"Jamba: Hybrid transformer-mamba language models","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Lenz"},{"key":"ref53","article-title":"TransMamba: Fast universal architecture adaption from transformers to mamba","author":"Chen","year":"2025","journal-title":"arXiv:2502.15130"},{"key":"ref54","article-title":"TransMamba: A sequence-level hybrid transformer-mamba language model","author":"Li","year":"2025","journal-title":"arXiv:2503.24067"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-87574-8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref60","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","volume":"1","author":"Kim"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref64","article-title":"General-purpose tagging of freesound audio with AudioSet labels: Task description, dataset, and baseline","author":"Fonseca","year":"2018","journal-title":"arXiv:1807.09902"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref66","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref67","article-title":"A reference-free metric for language-queried audio source separation using contrastive language-audio pretraining","author":"Xiao","year":"2024","journal-title":"arXiv:2407.04936"},{"issue":"1","key":"ref68","first-page":"524","article-title":"Dynamic time warping (dtw) algorithm in speech: a review","volume":"6","author":"Yadav","year":"2018","journal-title":"Int. J. Res. Electron. Comput. Eng."},{"issue":"1","key":"ref69","first-page":"795","article-title":"Algorithms for learning kernels based on centered alignment","volume":"13","author":"Cortes","year":"2012","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11359160.pdf?arnumber=11359160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:08:47Z","timestamp":1770671327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3656219","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}