{"id":"https://openalex.org/W2981541003","doi":"https://doi.org/10.1109/icassp40776.2020.9053327","title":"WHAMR!: Noisy and Reverberant Single-Channel Speech Separation","display_name":"WHAMR!: Noisy and Reverberant Single-Channel Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981541003","doi":"https://doi.org/10.1109/icassp40776.2020.9053327","mag":"2981541003"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.10279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054649622","display_name":"Matthew Maciejewski","orcid":"https://orcid.org/0000-0002-6336-2135"},"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":true,"raw_author_name":"Matthew Maciejewski","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"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/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","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"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/A5086679237","display_name":"Emmett McQuinn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmett McQuinn","raw_affiliation_strings":["Whisper.ai, San Francisco, CA, USA","Whisper.ai,San Francisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Whisper.ai, San Francisco, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Whisper.ai,San Francisco,CA,USA","institution_ids":[]}]},{"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","[Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA]"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5054649622"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":0.7614,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69311338,"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":"696","last_page":"700"},"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":0.9979000091552734,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/reverberation","display_name":"Reverberation","score":0.8511534929275513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7179403305053711},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.7095152735710144},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5929918885231018},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.582815945148468},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5495242476463318},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5257906913757324},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5046440362930298},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.46643900871276855},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4256819486618042},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41095757484436035},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3941827416419983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23837924003601074},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1883598268032074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10755953192710876},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06283894181251526}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8511534929275513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179403305053711},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.7095152735710144},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5929918885231018},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.582815945148468},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5495242476463318},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5257906913757324},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5046440362930298},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.46643900871276855},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4256819486618042},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41095757484436035},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3941827416419983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23837924003601074},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1883598268032074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10755953192710876},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06283894181251526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10279","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10279","pdf_url":"https://arxiv.org/pdf/1910.10279","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":null},{"id":"mag:2981541003","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.10279.pdf","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.1910.10279","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10279","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":"article"},{"id":"doi:10.17023/5dy5-0w38","is_oa":true,"landing_page_url":"https://doi.org/10.17023/5dy5-0w38","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.10279","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10279","pdf_url":"https://arxiv.org/pdf/1910.10279","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":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981541003.pdf","grobid_xml":"https://content.openalex.org/works/W2981541003.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1608304634","https://openalex.org/W2006129368","https://openalex.org/W2221409856","https://openalex.org/W2550143307","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2767071179","https://openalex.org/W2889540509","https://openalex.org/W2890244912","https://openalex.org/W2890820256","https://openalex.org/W2891405874","https://openalex.org/W2892163332","https://openalex.org/W2918296821","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2968723745","https://openalex.org/W2972541922","https://openalex.org/W2996969697","https://openalex.org/W2997696598","https://openalex.org/W4300098418","https://openalex.org/W6631190155","https://openalex.org/W6688843265","https://openalex.org/W6759323020"],"related_works":["https://openalex.org/W2736172179","https://openalex.org/W3026111682","https://openalex.org/W2599685671","https://openalex.org/W120286663","https://openalex.org/W2938297719","https://openalex.org/W1987750302","https://openalex.org/W2062355771","https://openalex.org/W2668911695","https://openalex.org/W1500260212","https://openalex.org/W2804228164","https://openalex.org/W3131090526","https://openalex.org/W3137952414","https://openalex.org/W2537814008","https://openalex.org/W2180309746","https://openalex.org/W2601568848","https://openalex.org/W3153879011","https://openalex.org/W2871284238","https://openalex.org/W2772504888","https://openalex.org/W2125539885","https://openalex.org/W2276077954"],"abstract_inverted_index":{"While":[0],"significant":[1,69],"advances":[2],"have":[3,16],"been":[4,17],"made":[5],"with":[6,105],"respect":[7],"to":[8,20,39,90],"the":[9,34,40,85,125],"separation":[10,77],"of":[11,22,29,57,87,103,115],"overlapping":[12],"speech":[13,76,88],"signals,":[14],"studies":[15],"largely":[18],"constrained":[19],"mixtures":[21],"clean,":[23],"near":[24],"anechoic":[25],"speech,":[26],"not":[27,46],"representative":[28],"many":[30],"real-world":[31],"scenarios.":[32],"Although":[33],"WHAM!":[35,104],"dataset":[36],"introduced":[37,127],"noise":[38],"ubiquitous":[41],"wsj0-2mix":[42],"dataset,":[43],"it":[44],"did":[45],"include":[47],"reverberation,":[48],"which":[49,79],"is":[50],"generally":[51],"present":[52],"in":[53,68],"indoor":[54],"recordings":[55],"outside":[56],"recording":[58],"studios.":[59],"The":[60],"spectral":[61,82],"smearing":[62],"caused":[63],"by":[64],"reverberation":[65],"can":[66],"result":[67],"performance":[70],"degradation":[71],"for":[72],"standard":[73],"deep":[74],"learning-based":[75],"systems,":[78],"rely":[80],"on":[81,124],"structure":[83],"and":[84,109],"sparsity":[86],"signals":[89],"tease":[91],"apart":[92],"sources.":[93],"To":[94],"address":[95],"this,":[96],"we":[97],"introduce":[98],"WHAMR!,":[99],"an":[100],"augmented":[101],"version":[102],"synthetic":[106],"reverberated":[107],"sources,":[108],"provide":[110],"a":[111],"thorough":[112],"baseline":[113],"analysis":[114],"current":[116],"techniques":[117],"as":[118,120],"well":[119],"novel":[121],"cascaded":[122],"architectures":[123],"newly":[126],"conditions.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}