{"id":"https://openalex.org/W3036069164","doi":null,"title":"Unsupervised Sound Separation Using Mixtures of Mixtures","display_name":"Unsupervised Sound Separation Using Mixtures of Mixtures","publication_year":2020,"publication_date":"2020-06-11","ids":{"openalex":"https://openalex.org/W3036069164","mag":"3036069164"},"language":"en","primary_location":{"id":"mag:3036069164","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=qMMzJGRPT2d","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428","observed_orcids":["https://orcid.org/0000-0001-6671-1428"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6671-1428","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016864112","display_name":"Efthymios Tzinis","orcid":"https://orcid.org/0000-0002-1047-1338","observed_orcids":["https://orcid.org/0000-0002-1047-1338"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1047-1338","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642","observed_orcids":["https://orcid.org/0000-0003-3140-8642"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakan Erdo\u011fan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3140-8642","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053","observed_orcids":["https://orcid.org/0000-0003-2010-4053"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2010-4053","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023061955","display_name":"Kirk Wilson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9141-2219","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9126,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94698176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9160000085830688,"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":0.9160000085830688,"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":0.07039999961853027,"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":0.010400000028312206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/single-channel-speech-separation","display_name":"single-channel speech separation","score":0.7129999995231628},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.6740000247955322},{"id":"https://openalex.org/keywords/unsupervised-domain-adaptation","display_name":"unsupervised domain adaptation","score":0.9549999833106995},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662233293056488},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5194151401519775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5190418362617493},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5056171417236328},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4959474503993988},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49217692017555237},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.47265732288360596},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4363487660884857},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.43168362975120544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41935837268829346},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41753190755844116},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4147719740867615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3575640320777893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3542550504207611},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1706395447254181},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0840514600276947},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3036069164","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=qMMzJGRPT2d","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1494198834","https://openalex.org/W1731081199","https://openalex.org/W1897240248","https://openalex.org/W1963835294","https://openalex.org/W2031647436","https://openalex.org/W2099128937","https://openalex.org/W2106582496","https://openalex.org/W2149648698","https://openalex.org/W2168793898","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2511131004","https://openalex.org/W2584009249","https://openalex.org/W2593116425","https://openalex.org/W2593768305","https://openalex.org/W2765407302","https://openalex.org/W2770119437","https://openalex.org/W2892163332","https://openalex.org/W2899515918","https://openalex.org/W2899647550","https://openalex.org/W2900368655","https://openalex.org/W2900541487","https://openalex.org/W2905258586","https://openalex.org/W2933708090","https://openalex.org/W2943865428","https://openalex.org/W2944338086","https://openalex.org/W2952218014","https://openalex.org/W2964121744","https://openalex.org/W2964204553","https://openalex.org/W2973372147","https://openalex.org/W2982208454","https://openalex.org/W2988200020","https://openalex.org/W3015794161","https://openalex.org/W3090388844","https://openalex.org/W3095868011"],"related_works":["https://openalex.org/W3100954996","https://openalex.org/W3168140565","https://openalex.org/W3206116612","https://openalex.org/W4312540993","https://openalex.org/W4224951806","https://openalex.org/W4385822289","https://openalex.org/W4372271362","https://openalex.org/W7138256172","https://openalex.org/W3197103473","https://openalex.org/W2899647550"],"abstract_inverted_index":{"In":[0,22,101,120,194],"recent":[1],"years,":[2],"rapid":[3],"progress":[4],"has":[5],"been":[6],"made":[7],"on":[8,47,168],"the":[9,26,32,59,64,74,91,132,145,153],"problem":[10],"of":[11,18,61,73,79,93,140,187,225],"single-channel":[12,117],"sound":[13,94,218],"separation":[14,201,219],"using":[15],"supervised":[16,24,166],"training":[17,50,65,112,122],"deep":[19],"neural":[20],"networks.":[21],"such":[23,143],"approaches,":[25],"model":[27,133],"is":[28,52],"trained":[29],"to":[30,87,99,151,165],"predict":[31],"component":[33],"sources":[34,147],"from":[35,184,212],"synthetic":[36,49],"mixtures":[37],"created":[38],"by":[39,126,203,220],"adding":[40],"up":[41],"isolated":[42],"ground-truth":[43,191],"sources.":[44,80],"The":[45,81],"reliance":[46],"this":[48,102],"data":[51,66,189],"problematic":[53],"because":[54],"good":[55],"performance":[56,163,202],"depends":[57],"upon":[58],"degree":[60],"match":[62],"between":[63],"and":[67,77,90,131,182,215],"real-world":[68,188],"audio,":[69],"especially":[70],"in":[71,173],"terms":[72],"acoustic":[75,82,118],"conditions":[76],"distribution":[78,92],"properties":[83],"can":[84,148,160],"be":[85,97,149],"challenging":[86],"accurately":[88],"simulate,":[89],"types":[95],"may":[96],"hard":[98],"replicate.":[100],"paper,":[103],"we":[104,196],"propose":[105],"a":[106,137,174,208,222],"completely":[107],"unsupervised":[108,179],"method,":[109],"mixture":[110],"invariant":[111],"(MixIT),":[113],"that":[114,144,158],"requires":[115],"only":[116],"mixtures.":[119,155],"MixIT,":[121],"examples":[123],"are":[124],"constructed":[125],"mixing":[127],"together":[128],"existing":[129],"mixtures,":[130,206,214],"separates":[134],"them":[135],"into":[136],"variable":[138],"number":[139],"latent":[141],"sources,":[142],"separated":[146],"remixed":[150],"approximate":[152],"original":[154],"We":[156],"show":[157],"MixIT":[159,172],"achieve":[161],"competitive":[162],"compared":[164],"methods":[167],"speech":[169,200,209],"separation.":[170],"Using":[171],"semi-supervised":[175],"learning":[176,183],"setting":[177],"enables":[178],"domain":[180],"adaptation":[181],"large":[185,223],"amounts":[186],"without":[190],"source":[192],"waveforms.":[193],"particular,":[195],"significantly":[197],"improve":[198,216],"reverberant":[199,205],"incorporating":[204,221],"train":[207],"enhancement":[210],"system":[211],"noisy":[213],"universal":[217],"amount":[224],"in-the-wild":[226],"data.":[227]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-06-25T00:00:00"}