{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:06Z","timestamp":1775229906860,"version":"3.50.1"},"reference-count":44,"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\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","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\/icassp49660.2025.10890324","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":7,"title":["DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification"],"prefix":"10.1109","author":[{"given":"Dongheon","family":"Lee","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Woo","family":"Choi","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053921"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3290428"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3357036"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3244428"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-696"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446396"},{"key":"ref17","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref18","article-title":"Efficiently Modeling Long Sequences with Structured State Spaces","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Gu"},{"key":"ref19","article-title":"Simplified state space layers for sequence modeling","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Smith"},{"key":"ref20","article-title":"SPmamba: State-space model is all you need in speech separation","author":"Li","year":"2024"},{"key":"ref21","article-title":"Dual-path mamba: Short and long-term bidirectional selective structured state space models for speech separation","author":"Jiang","year":"2024"},{"key":"ref22","article-title":"Mamba in speech: Towards an alternative to self-attention","author":"Zhang","year":"2024"},{"key":"ref23","article-title":"STARSS23: Sony-tau realistic spatial soundscapes 2023","author":"Politis","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690575"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2024.3483009","article-title":"Audio mamba: Bidirectional state space model for audio representation learning","author":"Erol","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"},{"key":"ref29","article-title":"DeFTAN-II: Efficient multichannel speech enhancement with subgroup processing","author":"Lee","year":"2023"},{"key":"ref30","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Dao"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-669"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.191"},{"key":"ref33","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746757"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3310881"},{"issue":"1\/2","key":"ref43","first-page":"3","article-title":"PEAQ-the ITU standard for objective measurement of perceived audio quality","volume":"48","author":"Thiede","year":"2000","journal-title":"J. Audio Eng. Soc."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393713"}],"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\/10890324.pdf?arnumber=10890324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:02Z","timestamp":1774416362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890324","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}