{"id":"https://openalex.org/W3214314684","doi":"https://doi.org/10.1109/icassp43922.2022.9746973","title":"Unsupervised Speech Enhancement with Speech Recognition Embedding and Disentanglement Losses","display_name":"Unsupervised Speech Enhancement with Speech Recognition Embedding and Disentanglement Losses","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3214314684","doi":"https://doi.org/10.1109/icassp43922.2022.9746973","mag":"3214314684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746973","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.08678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]},{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["CUNY,The Graduate Center,NY,USA","City University of New York"],"affiliations":[{"raw_affiliation_string":"CUNY,The Graduate Center,NY,USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research,Redmond,WA,USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085746637"],"corresponding_institution_ids":["https://openalex.org/I121847817","https://openalex.org/I174216632"],"apc_list":null,"apc_paid":null,"fwci":0.1221,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19269521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"395"},"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":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.766711950302124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6912907958030701},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6753540635108948},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6183346509933472},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5582301020622253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5089688301086426},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4762461483478546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33691608905792236},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27115803956985474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766711950302124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6912907958030701},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6753540635108948},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6183346509933472},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5582301020622253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089688301086426},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4762461483478546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33691608905792236},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27115803956985474},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746973","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"},{"id":"pmh:oai:arXiv.org:2111.08678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.08678","pdf_url":"https://arxiv.org/pdf/2111.08678","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":null,"raw_type":"text"},{"id":"mag:3214314684","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.08678","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.2111.08678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.08678","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/g1ka-ge41","is_oa":true,"landing_page_url":"https://doi.org/10.17023/g1ka-ge41","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:2111.08678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.08678","pdf_url":"https://arxiv.org/pdf/2111.08678","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3214314684.pdf","grobid_xml":"https://content.openalex.org/works/W3214314684.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889118710","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964199361","https://openalex.org/W2987307811","https://openalex.org/W2991361823","https://openalex.org/W3026827614","https://openalex.org/W3035837245","https://openalex.org/W3088490496","https://openalex.org/W3099782249","https://openalex.org/W3100954996","https://openalex.org/W3122264812","https://openalex.org/W3126409868","https://openalex.org/W3160129476","https://openalex.org/W3161140524","https://openalex.org/W3161480375","https://openalex.org/W3164223074","https://openalex.org/W3191448984","https://openalex.org/W3193786050","https://openalex.org/W3197042120","https://openalex.org/W4225325562","https://openalex.org/W6779216093","https://openalex.org/W6780218876","https://openalex.org/W6784499681","https://openalex.org/W6791429105","https://openalex.org/W6795747053"],"related_works":["https://openalex.org/W3207551191","https://openalex.org/W3011500442","https://openalex.org/W3199713199","https://openalex.org/W3164736513","https://openalex.org/W3031135612","https://openalex.org/W3005262054","https://openalex.org/W3163142165","https://openalex.org/W3015893539","https://openalex.org/W2296167893","https://openalex.org/W2972592847","https://openalex.org/W2941290535","https://openalex.org/W3142629163","https://openalex.org/W3209376089","https://openalex.org/W2572023240","https://openalex.org/W3149225678","https://openalex.org/W3164223074","https://openalex.org/W2548494187","https://openalex.org/W2963954250","https://openalex.org/W3041487835","https://openalex.org/W2963364041"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,16,36,73,121],"has":[2],"recently":[3],"achieved":[4],"great":[5],"success":[6],"with":[7,20,103,148],"various":[8],"deep":[9],"learning":[10],"methods.":[11],"However,":[12],"most":[13],"conventional":[14],"speech":[15,35,43,62,72,77,104,120,161],"systems":[17,37],"are":[18,38],"trained":[19,127],"supervised":[21,130,170],"methods":[22],"that":[23,113],"impose":[24],"two":[25,91],"significant":[26],"challenges.":[27],"First,":[28],"a":[29,68,125,129],"majority":[30],"of":[31,60],"training":[32,140],"datasets":[33],"for":[34],"synthetic.":[39],"When":[40],"mixing":[41],"clean":[42],"and":[44,57,75,107,151,163],"noisy":[45,61,134],"corpora":[46],"to":[47,88,124,143,158],"create":[48],"the":[49,99,114,119,133,145,154,168],"synthetic":[50,56],"datasets,":[51],"domain":[52],"mismatches":[53],"occur":[54],"between":[55,70],"real-world":[58],"recordings":[59],"or":[63],"audio.":[64],"Second,":[65],"there":[66],"is":[67,95,141,156],"trade-off":[69],"increasing":[71],"performance":[74,122,166],"degrading":[76],"recognition":[78,105],"(ASR)":[79],"performance.":[80],"Thus,":[81],"we":[82],"propose":[83],"an":[84],"unsupervised":[85,139,152],"loss":[86,101],"function":[87,94,102,116],"tackle":[89],"those":[90],"problems.":[92],"Our":[93,110],"developed":[96],"by":[97],"extending":[98],"MixIT":[100],"embedding":[106],"disentanglement":[108],"loss.":[109],"results":[111],"show":[112],"proposed":[115],"effectively":[117],"improves":[118],"compared":[123],"baseline":[126],"in":[128],"way":[131],"on":[132],"VoxCeleb":[135],"dataset.":[136],"While":[137],"fully":[138],"unable":[142],"exceed":[144],"corresponding":[146],"baseline,":[147],"joint":[149],"super-":[150],"training,":[153],"system":[155],"able":[157],"achieve":[159],"similar":[160],"quality":[162],"better":[164],"ASR":[165],"than":[167],"best":[169],"baseline.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-08-14T00:00:00"}