{"id":"https://openalex.org/W4408353280","doi":"https://doi.org/10.1109/icassp49660.2025.10890324","title":"DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification","display_name":"DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353280","doi":"https://doi.org/10.1109/icassp49660.2025.10890324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008565279","display_name":"Dongheon Lee","orcid":"https://orcid.org/0000-0003-4660-6174"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongheon Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017443019","display_name":"Jungwoo Choi","orcid":"https://orcid.org/0000-0003-3988-6331"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Woo Choi","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Electrical Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8898043632507324},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5543918013572693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.518300473690033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5170744061470032},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4173760712146759},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.355855792760849},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09457099437713623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.053557127714157104}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8898043632507324},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5543918013572693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.518300473690033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5170744061470032},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4173760712146759},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.355855792760849},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09457099437713623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.053557127714157104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2143169494","https://openalex.org/W2460742184","https://openalex.org/W2526050071","https://openalex.org/W2591013610","https://openalex.org/W2898268964","https://openalex.org/W2938440247","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3048593389","https://openalex.org/W3096893582","https://openalex.org/W3161934504","https://openalex.org/W3161950572","https://openalex.org/W3196974791","https://openalex.org/W3210390090","https://openalex.org/W4205689591","https://openalex.org/W4225299287","https://openalex.org/W4233392025","https://openalex.org/W4321608474","https://openalex.org/W4372348953","https://openalex.org/W4375928773","https://openalex.org/W4384160435","https://openalex.org/W4385756463","https://openalex.org/W4385823047","https://openalex.org/W4386320488","https://openalex.org/W4391621214","https://openalex.org/W4392903216","https://openalex.org/W4392903555","https://openalex.org/W4392909548","https://openalex.org/W4395471087","https://openalex.org/W4402112019","https://openalex.org/W4403511013","https://openalex.org/W6636045042","https://openalex.org/W6766320909","https://openalex.org/W6803444062","https://openalex.org/W6841205203","https://openalex.org/W6854308872","https://openalex.org/W6855817434","https://openalex.org/W6859298233","https://openalex.org/W6862687296","https://openalex.org/W6863185053","https://openalex.org/W6863679278","https://openalex.org/W6868207820","https://openalex.org/W6868789466"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24,71,82,118],"framework":[4,112],"for":[5],"universal":[6,120],"sound":[7,21,43,121],"separation":[8,66,122],"and":[9,18,54,67,115,136,139],"polyphonic":[10,142],"audio":[11],"classification,":[12],"addressing":[13],"the":[14,32,46,55,91],"challenges":[15],"of":[16,93,141],"separating":[17],"classifying":[19],"individual":[20],"sources":[22,135],"in":[23,75,125],"multichannel":[25,119],"mixture.":[26],"The":[27,110],"proposed":[28,105,111],"framework,":[29],"DeFT-Mamba,":[30],"utilizes":[31],"dense":[33],"frequency-time":[34],"attentive":[35],"network":[36],"(DeFTAN)":[37],"combined":[38],"with":[39,133],"Mamba":[40],"to":[41,89,106,129],"extract":[42],"objects,":[44],"capturing":[45],"local":[47],"time-frequency":[48,57],"relations":[49,58],"through":[50,59],"gated":[51],"convolution":[52],"block":[53],"global":[56],"position-wise":[60],"Hybrid":[61],"Mamba.":[62],"DeFT-Mamba":[63],"surpasses":[64],"existing":[65],"classification":[68],"networks":[69],"by":[70],"large":[72],"margin,":[73],"particularly":[74],"complex":[76],"scenarios":[77],"involving":[78],"in-class":[79],"polyphony.":[80],"Additionally,":[81],"classification-based":[83],"source":[84],"counting":[85],"method":[86],"is":[87,103,113],"introduced":[88],"identify":[90],"presence":[92],"multiple":[94],"sources,":[95],"outperforming":[96],"conventional":[97],"threshold-based":[98],"approaches.":[99],"Separation":[100],"refinement":[101],"tuning":[102],"also":[104],"improve":[107],"performance":[108],"further.":[109],"trained":[114],"tested":[116],"on":[117],"dataset":[123],"developed":[124],"this":[126],"work,":[127],"designed":[128],"mimic":[130],"realistic":[131],"environments":[132],"moving":[134],"varying":[137],"onsets":[138],"offsets":[140],"events.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}