{"id":"https://openalex.org/W4225293699","doi":"https://doi.org/10.1109/icassp43922.2022.9747076","title":"Improving Source Separation by Explicitly Modeling Dependencies between Sources","display_name":"Improving Source Separation by Explicitly Modeling Dependencies between Sources","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225293699","doi":"https://doi.org/10.1109/icassp43922.2022.9747076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5023355857","display_name":"Ethan Manilow","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Ethan Manilow","raw_affiliation_strings":["Google Research,Brain Team","Brain Team, Google Research","Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Brain Team, Google Research","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083209727","display_name":"Curtis Hawthorne","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Curtis Hawthorne","raw_affiliation_strings":["Google Research,Brain Team","Brain Team, Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Brain Team, Google Research","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007555810","display_name":"Cheng-Zhi Anna Huang","orcid":"https://orcid.org/0009-0009-4194-0393"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Cheng-Zhi Anna Huang","raw_affiliation_strings":["Google Research,Brain Team","Brain Team, Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Brain Team, Google Research","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048688198","display_name":"Jesse Engel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Jesse Engel","raw_affiliation_strings":["Google Research,Brain Team","Brain Team, Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]},{"raw_affiliation_string":"Brain Team, Google Research","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5537,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59015266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"291","last_page":"295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7332862615585327},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.7258659601211548},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6597756147384644},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5876567959785461},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.585067093372345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48895061016082764},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4309021234512329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4274473786354065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3680241107940674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33525943756103516},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23055905103683472},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15291446447372437},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08577132225036621},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.07299754023551941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7332862615585327},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.7258659601211548},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6597756147384644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5876567959785461},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.585067093372345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48895061016082764},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4309021234512329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4274473786354065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3680241107940674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33525943756103516},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23055905103683472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15291446447372437},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08577132225036621},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.07299754023551941},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":38,"referenced_works":["https://openalex.org/W2166942303","https://openalex.org/W2519091744","https://openalex.org/W2764251778","https://openalex.org/W2896457183","https://openalex.org/W2898963093","https://openalex.org/W2952295562","https://openalex.org/W2952428868","https://openalex.org/W2954304925","https://openalex.org/W2962753171","https://openalex.org/W2964005873","https://openalex.org/W2964058413","https://openalex.org/W2969034647","https://openalex.org/W2972411915","https://openalex.org/W2990594533","https://openalex.org/W2991107219","https://openalex.org/W2998490864","https://openalex.org/W3015213533","https://openalex.org/W3015268063","https://openalex.org/W3015753416","https://openalex.org/W3037149862","https://openalex.org/W3106104628","https://openalex.org/W3160050861","https://openalex.org/W4286910219","https://openalex.org/W4287083626","https://openalex.org/W4287180975","https://openalex.org/W4288089799","https://openalex.org/W4298310324","https://openalex.org/W6684870364","https://openalex.org/W6744574196","https://openalex.org/W6745704996","https://openalex.org/W6755207826","https://openalex.org/W6766320909","https://openalex.org/W6766938422","https://openalex.org/W6769627184","https://openalex.org/W6786621524","https://openalex.org/W6795742094","https://openalex.org/W6798447524","https://openalex.org/W6802395087"],"related_works":["https://openalex.org/W3146360815","https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W1570787356","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W2015759683","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270"],"abstract_inverted_index":{"We":[0,66,87],"propose":[1],"a":[2,7,25,34,59,68,112,133,150,171,176],"new":[3],"method":[4,110],"for":[5,77],"training":[6,94,109,149],"supervised":[8],"source":[9,32,39,53,70,134,139,144],"separation":[10,40,71,129,145],"system":[11],"that":[12,96,122,148,174],"aims":[13],"to":[14,83,163],"learn":[15],"the":[16,38,56,63,84,97,100,104,123],"interdependent":[17],"relationships":[18],"between":[19,103],"all":[20],"combinations":[21],"of":[22,62,185],"sources":[23,92],"in":[24,81],"mixture.":[26,86],"Rather":[27],"than":[28],"independently":[29],"estimating":[30],"each":[31,52,78],"from":[33,54],"mix,":[35],"we":[36,120],"reframe":[37],"problem":[41],"as":[42],"an":[43,154],"Orderless":[44,155],"Neural":[45],"Autoregressive":[46],"Density":[47],"Estimator":[48],"(NADE),":[49],"and":[50,58,158,180],"estimate":[51,135],"both":[55],"mix":[57],"random":[60],"subset":[61],"other":[64],"sources.":[65,105,186],"adapt":[67],"standard":[69,177],"architecture,":[72],"Demucs,":[73],"with":[74,111,153],"additional":[75],"inputs":[76],"individual":[79],"source,":[80],"addition":[82],"input":[85,91],"randomly":[88],"mask":[89],"these":[90],"during":[93],"so":[95],"network":[98,124],"learns":[99],"conditional":[101],"dependencies":[102],"By":[106],"pairing":[107],"this":[108],"blocked":[113],"Gibbs":[114,160],"sampling":[115,161],"procedure":[116],"at":[117,166],"inference":[118,167],"time,":[119],"demonstrate":[121],"can":[125],"iteratively":[126],"improve":[127],"its":[128,137],"performance":[130],"by":[131],"conditioning":[132],"on":[136,142],"earlier":[138],"estimates.":[140],"Experiments":[141],"two":[143],"datasets":[146],"show":[147],"Demucs":[151,172],"model":[152],"NADE":[156],"approach":[157],"using":[159],"(up":[162],"512":[164],"steps)":[165],"time":[168],"strongly":[169],"outperforms":[170],"baseline":[173],"uses":[175],"regression":[178],"loss":[179],"direct":[181],"(one":[182],"step)":[183],"estimation":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}