{"id":"https://openalex.org/W4226219411","doi":"https://doi.org/10.1109/asru51503.2021.9688176","title":"Incorporating Real-World Noisy Speech in Neural-Network-Based Speech Enhancement Systems","display_name":"Incorporating Real-World Noisy Speech in Neural-Network-Based Speech Enhancement Systems","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226219411","doi":"https://doi.org/10.1109/asru51503.2021.9688176"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688176","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5104037412","display_name":"Yangyang Xia","orcid":null},"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":true,"raw_author_name":"Yangyang Xia","raw_affiliation_strings":["Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Facebook Reality Labs Research,Redmond,WA,USA,98052"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs Research,Redmond,WA,USA,98052"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104037412"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.2042,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87038281,"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":"564","last_page":"570"},"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":0.9986000061035156,"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":0.9976000189781189,"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/autoencoder","display_name":"Autoencoder","score":0.7930349111557007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747546434402466},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7661612033843994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604375422000885},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5648595094680786},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5420480966567993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202144980430603},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5158818960189819},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4270179867744446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494388461112976},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1376972496509552},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.083224356174469}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7930349111557007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747546434402466},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7661612033843994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604375422000885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5648595094680786},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5420480966567993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202144980430603},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5158818960189819},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4270179867744446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494388461112976},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1376972496509552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.083224356174469},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688176","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1574170747","https://openalex.org/W2052666245","https://openalex.org/W2069681747","https://openalex.org/W2096733369","https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2752796333","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2952218014","https://openalex.org/W2962793481","https://openalex.org/W2963420272","https://openalex.org/W2963799213","https://openalex.org/W2964058413","https://openalex.org/W3002439978","https://openalex.org/W3015644200","https://openalex.org/W3016120385","https://openalex.org/W3031135612","https://openalex.org/W3035837245","https://openalex.org/W3040498734","https://openalex.org/W3093839391","https://openalex.org/W3099330747","https://openalex.org/W3122264812","https://openalex.org/W6754901823","https://openalex.org/W6772622344","https://openalex.org/W6779216093","https://openalex.org/W6779503413","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2275432853","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Supervised":[0],"speech":[1,9,26,48,56,65,98,117],"enhancement":[2,49,66,93,118],"relies":[3],"on":[4,53],"parallel":[5],"databases":[6],"of":[7,23],"degraded":[8,25,55],"signals":[10,15],"and":[11],"their":[12],"clean":[13],"reference":[14],"during":[16],"training.":[17],"This":[18],"setting":[19],"prohibits":[20],"the":[21,32],"use":[22,85],"real-world":[24,54,96,113],"data":[27,99,114],"that":[28,45,77],"may":[29],"better":[30],"represent":[31],"scenarios":[33],"where":[34],"such":[35],"systems":[36,50],"are":[37],"used.":[38],"In":[39],"this":[40,86],"paper,":[41],"we":[42,59,69],"explore":[43],"methods":[44],"enable":[46],"supervised":[47],"to":[51,89],"train":[52,71,91],"data.":[57],"Specifically,":[58],"propose":[60],"a":[61,72,79,102],"semi-supervised":[62],"approach":[63],"for":[64,111],"in":[67,115],"which":[68],"first":[70],"modified":[73],"vector-quantized":[74],"variational":[75],"autoencoder":[76,88],"solves":[78],"source":[80],"separation":[81],"task.":[82],"We":[83],"then":[84],"trained":[87],"further":[90],"an":[92],"network":[94],"using":[95],"noisy":[97],"by":[100],"computing":[101],"triplet-based":[103],"unsupervised":[104],"loss":[105],"function.":[106],"Experiments":[107],"show":[108],"promising":[109],"results":[110],"incorporating":[112],"training":[116],"systems.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}