{"id":"https://openalex.org/W4296069305","doi":"https://doi.org/10.21437/interspeech.2022-10717","title":"Heterogeneous Target Speech Separation","display_name":"Heterogeneous Target Speech Separation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069305","doi":"https://doi.org/10.21437/interspeech.2022-10717"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10717","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10717","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5016864112","display_name":"Efthymios Tzinis","orcid":"https://orcid.org/0000-0002-1047-1338"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efthymios Tzinis","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"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":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1796","last_page":"1800"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9979000091552734,"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/separation","display_name":"Separation (statistics)","score":0.6913096904754639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429696679115295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44678816199302673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0988934338092804}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6913096904754639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429696679115295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44678816199302673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0988934338092804}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10717","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10717","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":35,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1991139021","https://openalex.org/W2001571181","https://openalex.org/W2046869671","https://openalex.org/W2078528584","https://openalex.org/W2082183045","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2760103357","https://openalex.org/W2763188033","https://openalex.org/W2774707525","https://openalex.org/W2891833136","https://openalex.org/W2909607850","https://openalex.org/W2936302822","https://openalex.org/W2938646939","https://openalex.org/W2962715207","https://openalex.org/W2962753171","https://openalex.org/W2962866211","https://openalex.org/W2963189033","https://openalex.org/W2964058413","https://openalex.org/W2972864514","https://openalex.org/W2973062255","https://openalex.org/W2990666817","https://openalex.org/W2991107219","https://openalex.org/W3094806148","https://openalex.org/W3095263845","https://openalex.org/W3162437887","https://openalex.org/W3165246035","https://openalex.org/W3191469971","https://openalex.org/W3197419327","https://openalex.org/W3198575250","https://openalex.org/W3215562486","https://openalex.org/W4288088464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,46],"new":[3,66,89],"paradigm":[4],"for":[5,135],"single-channel":[6],"target":[7],"source":[8,91,105,112],"separation":[9,31,57,92,113,127],"where":[10],"the":[11,63,108,130],"sources":[12],"of":[13,48,88,111,132],"interest":[14],"can":[15,33,96],"be":[16],"distinguished":[17],"using":[18],"non-mutually":[19],"exclusive":[20],"concepts":[21,49,67,94],"(e.g.,":[22],"loudness,":[23],"gender,":[24],"language,":[25],"spatial":[26],"location,":[27],"etc).Our":[28],"proposed":[29],"heterogeneous":[30,60,116],"framework":[32],"seamlessly":[34],"leverage":[35],"datasets":[36,137],"with":[37,59,68,103,115,125],"large":[38],"distribution":[39],"shifts":[40],"and":[41,95,118],"learn":[42],"cross-domain":[43],"representations":[44],"under":[45],"variety":[47],"used":[50,138],"as":[51],"conditioning.Our":[52],"experiments":[53],"show":[54],"that":[55],"training":[56,82,102,114],"models":[58],"conditions":[61],"facilitates":[62],"generalization":[64],"to":[65,84,121,139],"unseen":[69],"out-of-domain":[70],"data":[71],"while":[72],"also":[73],"performing":[74],"substantially":[75],"higher":[76],"than":[77],"single-domain":[78],"specialist":[79],"models.Notably,":[80],"such":[81],"leads":[83],"more":[85],"robust":[86],"learning":[87],"harder":[90],"discriminative":[93],"yield":[97],"improvements":[98],"over":[99],"permutation":[100],"invariant":[101],"oracle":[104],"selection.We":[106],"analyze":[107],"intrinsic":[109],"behavior":[110],"metadata":[117],"propose":[119],"ways":[120],"alleviate":[122],"emerging":[123],"problems":[124],"challenging":[126,145],"conditions.We":[128],"release":[129],"collection":[131],"preparation":[133],"recipes":[134],"all":[136],"further":[140],"promote":[141],"research":[142],"towards":[143],"this":[144],"task.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}