{"id":"https://openalex.org/W4372269936","doi":"https://doi.org/10.1109/icassp49357.2023.10096847","title":"Adversarial Permutation Invariant Training for Universal Sound Separation","display_name":"Adversarial Permutation Invariant Training for Universal Sound Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269936","doi":"https://doi.org/10.1109/icassp49357.2023.10096847"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT","NL"],"is_corresponding":true,"raw_author_name":"Emilian Postolache","raw_affiliation_strings":["Dolby Laboratories","Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044197796","display_name":"Joan Serr\u00e0","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069620223"],"corresponding_institution_ids":["https://openalex.org/I116121188","https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74835681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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":0.8050599098205566},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.7161616086959839},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.7109013795852661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659114360809326},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5517065525054932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4934186041355133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437282383441925},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4432038366794586},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4395417869091034},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.431557297706604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3948768675327301},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3319609463214874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28637540340423584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20954692363739014},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12914398312568665}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8050599098205566},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.7161616086959839},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.7109013795852661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659114360809326},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5517065525054932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4934186041355133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437282383441925},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4432038366794586},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4395417869091034},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.431557297706604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3948768675327301},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3319609463214874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28637540340423584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20954692363739014},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12914398312568665},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2460742184","https://openalex.org/W2770119437","https://openalex.org/W2774707525","https://openalex.org/W2800664709","https://openalex.org/W2889128774","https://openalex.org/W2935846637","https://openalex.org/W2952218014","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2963816101","https://openalex.org/W2964229681","https://openalex.org/W2970006822","https://openalex.org/W2972653970","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W2998657200","https://openalex.org/W3015700067","https://openalex.org/W3093839391","https://openalex.org/W3095166612","https://openalex.org/W3095999710","https://openalex.org/W3096831136","https://openalex.org/W3099330747","https://openalex.org/W3161766157","https://openalex.org/W3161934504","https://openalex.org/W3162366763","https://openalex.org/W3168140565","https://openalex.org/W3180355996","https://openalex.org/W4205689591","https://openalex.org/W4225261970","https://openalex.org/W6746278845","https://openalex.org/W6746914816","https://openalex.org/W6767111847","https://openalex.org/W6779841522","https://openalex.org/W6784499681","https://openalex.org/W6785363610"],"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/W2077498359"],"abstract_inverted_index":{"Universal":[0],"sound":[1],"separation":[2,114],"consists":[3],"of":[4,10,87,121],"separating":[5],"mixes":[6],"with":[7,34,41,54,64],"arbitrary":[8],"sounds":[9],"different":[11],"types,":[12],"and":[13,61,80],"permutation":[14],"invariant":[15],"training":[16,63],"(PIT)":[17],"is":[18],"used":[19,45],"to":[20,104],"train":[21],"source":[22,48,125],"agnostic":[23],"models":[24],"that":[25,70],"do":[26],"so.":[27],"In":[28],"this":[29,52],"work,":[30],"we":[31,82],"complement":[32],"PIT":[33,103],"adversarial":[35,59,102,122],"losses":[36,123],"but":[37],"find":[38,101],"it":[39],"challenging":[40],"the":[42,74,77,95,118],"standard":[43],"formulation":[44],"in":[46,94,112],"speech":[47],"separation.":[49,126],"We":[50,99],"overcome":[51],"challenge":[53],"a":[55,84],"novel":[56],"I-replacement":[57],"context-based":[58],"loss,":[60],"by":[62,71],"multiple":[65],"discriminators.":[66],"Our":[67],"experiments":[68],"show":[69],"simply":[72],"improving":[73],"loss":[75],"(keeping":[76],"same":[78],"model":[79],"dataset)":[81],"obtain":[83],"non-negligible":[85],"improvement":[86],"1.4":[88],"dB":[89],"SI-SNR":[90],"<inf":[91],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">I</inf>":[93],"reverberant":[96],"FUSS":[97],"dataset.":[98],"also":[100],"be":[105],"effective":[106],"at":[107],"reducing":[108],"spectral":[109],"holes,":[110],"ubiquitous":[111],"mask-based":[113],"models,":[115],"which":[116],"highlights":[117],"potential":[119],"relevance":[120],"for":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}