{"id":"https://openalex.org/W4224933800","doi":"https://doi.org/10.1109/icassp43922.2022.9746303","title":"Investigating Self-Supervised Learning for Speech Enhancement and Separation","display_name":"Investigating Self-Supervised Learning for Speech Enhancement and Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933800","doi":"https://doi.org/10.1109/icassp43922.2022.9746303"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746303","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/A5101619225","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-1238-8017"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zili Huang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078898845","display_name":"Shu-Wen Yang","orcid":"https://orcid.org/0000-0001-5503-9410"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shu-wen Yang","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing and HLTCOE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6837","last_page":"6841"},"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":0.9994999766349792,"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":0.9952999949455261,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7891714572906494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7270634770393372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6497806906700134},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5596393346786499},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5273557305335999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4669894576072693},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4610006809234619},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4496862292289734},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44317182898521423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3353298306465149},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.28672051429748535},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2630612552165985},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2536305785179138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13494688272476196},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.08893421292304993}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7891714572906494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270634770393372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6497806906700134},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5596393346786499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5273557305335999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4669894576072693},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4610006809234619},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4496862292289734},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44317182898521423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3353298306465149},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.28672051429748535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2630612552165985},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2536305785179138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13494688272476196},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.08893421292304993},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746303","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W2067295501","https://openalex.org/W2094721231","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2896457183","https://openalex.org/W2949558265","https://openalex.org/W2952218014","https://openalex.org/W2962739339","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2972541922","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W3005511757","https://openalex.org/W3015199127","https://openalex.org/W3015213852","https://openalex.org/W3015356564","https://openalex.org/W3020336359","https://openalex.org/W3027008958","https://openalex.org/W3034781633","https://openalex.org/W3035524453","https://openalex.org/W3035725276","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3097286738","https://openalex.org/W3097568057","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3135990229","https://openalex.org/W3136499730","https://openalex.org/W3161223924","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3197912330","https://openalex.org/W3198275944","https://openalex.org/W3198771897","https://openalex.org/W3198858531","https://openalex.org/W3206252155","https://openalex.org/W3208743843","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4232282348","https://openalex.org/W4237168004","https://openalex.org/W4297808394","https://openalex.org/W6629717138","https://openalex.org/W6753000030","https://openalex.org/W6755207826","https://openalex.org/W6762114000","https://openalex.org/W6768815455","https://openalex.org/W6769196770","https://openalex.org/W6771812881","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6784776607","https://openalex.org/W6785000729","https://openalex.org/W6787335539","https://openalex.org/W6791480293","https://openalex.org/W6802609832","https://openalex.org/W6803164887","https://openalex.org/W6803394801"],"related_works":["https://openalex.org/W2402466562","https://openalex.org/W2120771489","https://openalex.org/W4205619918","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2059119686","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Speech":[0,12],"enhancement":[1,13,33,51,67,115,135],"and":[2,34,40,52,68,77,95,116,118,136],"separation":[3,19,35,53,69,117,137],"are":[4,54],"two":[5],"fundamental":[6],"tasks":[7],"for":[8,124,139],"robust":[9],"speech":[10,18,22,66,114,134],"processing.":[11],"suppresses":[14],"background":[15],"noise":[16],"while":[17],"extracts":[20],"target":[21],"from":[23],"interfering":[24],"speakers.":[25],"Despite":[26],"a":[27],"great":[28],"number":[29],"of":[30],"supervised":[31],"learning-based":[32],"methods":[36,64],"having":[37],"been":[38],"proposed":[39],"achieving":[41],"good":[42],"performance,":[43],"studies":[44],"on":[45,65,75],"applying":[46],"self-supervised":[47],"learning":[48],"(SSL)":[49],"to":[50,111,113],"limited.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,101],"evaluate":[60],"13":[61],"SSL":[62,82,108],"upstream":[63],"downstream":[70],"tasks.":[71,126],"Our":[72,127],"experimental":[73],"results":[74],"Voicebank-DEMAND":[76],"Libri2Mix":[78],"show":[79],"that":[80,105],"some":[81],"representations":[83],"consistently":[84],"outperform":[85],"baseline":[86],"features":[87],"including":[88],"the":[89,103,120,132],"short-time":[90],"Fourier":[91],"transform":[92],"(STFT)":[93],"magnitude":[94],"log":[96],"Mel":[97],"filterbank":[98],"(FBANK).":[99],"Furthermore,":[100],"analyze":[102],"factors":[104],"make":[106],"existing":[107],"frameworks":[109],"difficult":[110],"apply":[112],"discuss":[119],"representation":[121],"properties":[122],"desired":[123],"both":[125],"study":[128],"is":[129],"included":[130],"as":[131],"official":[133],"downstreams":[138],"SUPERB.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}