{"id":"https://openalex.org/W2954031873","doi":"https://doi.org/10.21437/interspeech.2019-2821","title":"WHAM!: Extending Speech Separation to Noisy Environments","display_name":"WHAM!: Extending Speech Separation to Noisy Environments","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2954031873","doi":"https://doi.org/10.21437/interspeech.2019-2821","mag":"2954031873"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.01160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057670329","display_name":"Joe Antognini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joe Antognini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023332016","display_name":"M. D. Flynn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Flynn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038900598","display_name":"Licheng Richard Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Licheng Richard Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086679237","display_name":"Emmett McQuinn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmett McQuinn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058765617","display_name":"Dwight Crow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dwight Crow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023355857","display_name":"Ethan Manilow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ethan Manilow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","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":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1368","last_page":"1372"},"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":0.9994000196456909,"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":0.9972000122070312,"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/robustness","display_name":"Robustness (evolution)","score":0.8049453496932983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025420069694519},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6078336834907532},{"id":"https://openalex.org/keywords/ambient-noise-level","display_name":"Ambient noise level","score":0.5956441164016724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5705448985099792},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.562300443649292},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5418700575828552},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4858517348766327},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4551503658294678},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44761404395103455},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.421987920999527},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2715434432029724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26617079973220825},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19980061054229736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1879577338695526},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09534004330635071},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07768163084983826}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8049453496932983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025420069694519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6078336834907532},{"id":"https://openalex.org/C205312793","wikidata":"https://www.wikidata.org/wiki/Q16002801","display_name":"Ambient noise level","level":3,"score":0.5956441164016724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5705448985099792},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.562300443649292},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5418700575828552},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4858517348766327},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4551503658294678},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44761404395103455},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.421987920999527},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2715434432029724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26617079973220825},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19980061054229736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1879577338695526},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09534004330635071},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07768163084983826},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.01160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01160","pdf_url":"https://arxiv.org/pdf/1907.01160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2954031873","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.01160v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.01160","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.01160","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.01160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.01160","pdf_url":"https://arxiv.org/pdf/1907.01160","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954031873.pdf","grobid_xml":"https://content.openalex.org/works/W2954031873.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2046869671","https://openalex.org/W2153331367","https://openalex.org/W2171878011","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2550143307","https://openalex.org/W2734774145","https://openalex.org/W2891405874","https://openalex.org/W2894785362","https://openalex.org/W2900132857","https://openalex.org/W2942172990","https://openalex.org/W2962715207","https://openalex.org/W2962728945","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963317762","https://openalex.org/W2996969697","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W2972541922","https://openalex.org/W3027008958","https://openalex.org/W3161301466","https://openalex.org/W3008880747","https://openalex.org/W3032969657","https://openalex.org/W3161305977","https://openalex.org/W3107686772","https://openalex.org/W3093979239","https://openalex.org/W3164223074","https://openalex.org/W3096915137","https://openalex.org/W3205293880","https://openalex.org/W2996820600","https://openalex.org/W2288838913","https://openalex.org/W2556036386","https://openalex.org/W2997696598","https://openalex.org/W3037383957","https://openalex.org/W3003231992","https://openalex.org/W3196705474","https://openalex.org/W87396816","https://openalex.org/W2002111936"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,29,101,107],"separating":[3],"the":[4,22,62,75,88,108,149],"speech":[5,121],"signals":[6,151],"from":[7,87],"multiple":[8],"overlapping":[9],"speakers":[10,40],"using":[11],"a":[12,33,138],"single":[13],"audio":[14],"channel":[15],"has":[16],"brought":[17],"us":[18],"closer":[19],"to":[20,60,127,131,148],"solving":[21],"cocktail":[23],"party":[24],"problem.":[25],"However,":[26],"most":[27,153],"studies":[28],"this":[30,56],"area":[31],"use":[32],"constrained":[34],"problem":[35],"setup,":[36],"comparing":[37],"performance":[38,135],"when":[39],"overlap":[41],"almost":[42],"completely,":[43],"at":[44],"artificially":[45],"low":[46],"sampling":[47],"rates,":[48],"and":[49,67,105,113,124],"with":[50,92],"no":[51],"external":[52],"background":[53],"noise.":[54,132],"In":[55],"paper,":[57],"we":[58,73,142],"strive":[59],"move":[61],"field":[63],"towards":[64],"more":[65],"realistic":[66],"challenging":[68],"scenarios.":[69],"To":[70],"that":[71],"end,":[72],"created":[74],"WSJ0":[76],"Hipster":[77],"Ambient":[78],"Mixtures":[79],"(WHAM!)":[80],"dataset,":[81],"consisting":[82],"of":[83,140],"two":[84],"speaker":[85],"mixtures":[86],"wsj0-2mix":[89],"dataset":[90],"combined":[91],"real":[93],"ambient":[94],"noise":[95],"samples.":[96],"The":[97],"samples":[98],"were":[99],"collected":[100],"coffee":[102],"shops,":[103],"restaurants,":[104],"bars":[106],"San":[109],"Francisco":[110],"Bay":[111],"Area,":[112],"are":[114],"made":[115],"publicly":[116],"available.":[117],"We":[118],"benchmark":[119],"various":[120],"separation":[122,134],"architectures":[123],"objective":[125],"functions":[126],"evaluate":[128],"their":[129],"robustness":[130],"While":[133],"decreases":[136],"as":[137],"result":[139],"noise,":[141],"still":[143],"observe":[144],"substantial":[145],"gains":[146],"relative":[147],"noisy":[150],"for":[152],"approaches.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}