{"id":"https://openalex.org/W4392909497","doi":"https://doi.org/10.1109/icassp48485.2024.10446705","title":"MDX-GAN: Enhancing Perceptual Quality in Multi-Class Source Separation Via Adversarial Training","display_name":"MDX-GAN: Enhancing Perceptual Quality in Multi-Class Source Separation Via Adversarial Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909497","doi":"https://doi.org/10.1109/icassp48485.2024.10446705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego","Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8270093202590942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641417741775513},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5739911794662476},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5630755424499512},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5361108183860779},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4940066933631897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.470716655254364},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1354101598262787},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05101028084754944}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8270093202590942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641417741775513},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5739911794662476},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5630755424499512},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5361108183860779},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4940066933631897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.470716655254364},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1354101598262787},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05101028084754944},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2086381917","https://openalex.org/W2094721231","https://openalex.org/W2410879554","https://openalex.org/W2555915854","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2964243274","https://openalex.org/W2988157778","https://openalex.org/W2990594533","https://openalex.org/W3004910802","https://openalex.org/W3015338123","https://openalex.org/W3015371781","https://openalex.org/W3015676952","https://openalex.org/W3096159803","https://openalex.org/W3099330747","https://openalex.org/W3161934504","https://openalex.org/W3197273793","https://openalex.org/W4224871700","https://openalex.org/W4225261970","https://openalex.org/W4226151502","https://openalex.org/W4372260250","https://openalex.org/W4372260310","https://openalex.org/W4375928773","https://openalex.org/W4376632781","https://openalex.org/W4385750366","https://openalex.org/W6767111847","https://openalex.org/W6779841522","https://openalex.org/W6783867762","https://openalex.org/W6801426729","https://openalex.org/W6801629112","https://openalex.org/W6804608017","https://openalex.org/W6838843145","https://openalex.org/W6842463588","https://openalex.org/W6852871851","https://openalex.org/W6855917767"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Audio":[0],"source":[1,16,55,76,168],"separation":[2,17],"aims":[3],"to":[4,36,69,107,119,140],"extract":[5],"individual":[6],"sound":[7,62,122,167],"sources":[8],"from":[9],"an":[10,50],"audio":[11,54,75],"mixture.":[12],"Recent":[13],"studies":[14],"on":[15,20,58,84,143,153],"focus":[18],"primarily":[19],"minimizing":[21],"signal-level":[22],"distance,":[23],"typically":[24],"measured":[25],"by":[26],"source-to-distortion":[27],"ratio":[28],"(SDR).":[29],"However,":[30],"scant":[31],"attention":[32],"has":[33],"been":[34],"given":[35],"the":[37,41,71,87,98,109,117,148,154,166],"perceptual":[38,72,110,155,172],"quality":[39,73,111,156],"of":[40,74,86,112,150],"separated":[42],"tracks.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,79,115],"propose":[48],"MDX-GAN,":[49],"efficient":[51],"and":[52,93,96,104,137,146,157,169],"high-fidelity":[53],"separator":[56],"based":[57],"MDX-Net":[59],"for":[60],"multiple":[61,121],"classes.":[63],"We":[64,133],"leverage":[65],"different":[66],"training":[67,100],"objectives":[68],"enhance":[70],"separation.":[77,113],"Specifically,":[78],"adopt":[80],"perceptually-motivated":[81],"loss":[82],"functions":[83],"top":[85],"waveform":[88],"loss,":[89],"including":[90],"multi-resolution":[91],"STFT":[92],"Mel-spectrogram":[94],"losses,":[95],"employ":[97],"adversarial":[99],"paradigm":[101],"with":[102],"multi-domain":[103],"multi-scale":[105],"discriminators":[106],"refine":[108],"Additionally,":[114],"extend":[116],"model":[118],"support":[120],"classes":[123],"within":[124],"a":[125],"single":[126],"network":[127],"via":[128],"feature-wise":[129],"linear":[130],"modulation":[131],"(FiLM).":[132],"conduct":[134],"both":[135],"objective":[136],"subjective":[138],"experiments":[139],"evaluate":[141],"MDX-GAN":[142,163],"real-world":[144],"settings,":[145],"assess":[147],"impacts":[149],"design":[151],"components":[152],"SDR":[158],"scores.":[159],"Results":[160],"demonstrate":[161],"that":[162],"accurately":[164],"separates":[165],"achieves":[170],"superior":[171],"quality.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}