{"id":"https://openalex.org/W3194338569","doi":"https://doi.org/10.21437/interspeech.2021-220","title":"Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement","display_name":"Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3194338569","doi":"https://doi.org/10.21437/interspeech.2021-220","mag":"3194338569"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-220","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sefik Emre Eskimez","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106627865","display_name":"Min Tang","orcid":"https://orcid.org/0009-0006-3428-9967"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039530233","display_name":"Hemin Yang","orcid":"https://orcid.org/0000-0001-7717-8163"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hemin Yang","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046470928","display_name":"Zirun Zhu","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zirun Zhu","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528069","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0002-4434-7482"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaming Wang","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2686","last_page":"2690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9962999820709229,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/closed-captioning","display_name":"Closed captioning","score":0.9324594736099243},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.812716543674469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530398368835449},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6957132816314697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6187514066696167},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.585056722164154},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47493866086006165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27189236879348755},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14590972661972046},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09279182553291321},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0858561098575592}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9324594736099243},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.812716543674469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530398368835449},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6957132816314697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6187514066696167},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.585056722164154},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47493866086006165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27189236879348755},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14590972661972046},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09279182553291321},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0858561098575592},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-220","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1499999342","https://openalex.org/W1552314771","https://openalex.org/W1597121597","https://openalex.org/W1897240248","https://openalex.org/W2130361043","https://openalex.org/W2141998673","https://openalex.org/W2327501763","https://openalex.org/W2346842942","https://openalex.org/W2398972335","https://openalex.org/W2407685581","https://openalex.org/W2577366047","https://openalex.org/W2589857635","https://openalex.org/W2593116425","https://openalex.org/W2636483419","https://openalex.org/W2755891984","https://openalex.org/W2770119437","https://openalex.org/W2921496354","https://openalex.org/W2939248538","https://openalex.org/W2949756029","https://openalex.org/W2963341071","https://openalex.org/W2987307811","https://openalex.org/W2998161426","https://openalex.org/W2998616931","https://openalex.org/W3015312544","https://openalex.org/W3016155933","https://openalex.org/W3033915435","https://openalex.org/W3034763882","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3140783160","https://openalex.org/W3160129476","https://openalex.org/W3196321886","https://openalex.org/W4295312788","https://openalex.org/W4301350573","https://openalex.org/W4394641246"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"With":[0],"the":[1,37,55,106,112,122,140,144,149,158,168,171,175,178,181],"surge":[2],"of":[3,39,180],"online":[4],"meetings,":[5],"it":[6],"has":[7],"become":[8],"more":[9],"critical":[10],"than":[11],"ever":[12],"to":[13,53,59,101,120],"provide":[14],"high-quality":[15],"speech":[16,27,44],"audio":[17],"and":[18,34,81,86,90,115,177],"live":[19],"captioning":[20],"under":[21],"various":[22],"noise":[23],"conditions.However,":[24],"most":[25,61],"monaural":[26],"enhancement":[28],"(SE)":[29],"models":[30,57,133],"introduce":[31],"processing":[32],"artifacts":[33],"thus":[35],"degrade":[36],"performance":[38],"downstream":[40],"tasks,":[41],"including":[42],"automatic":[43],"recognition":[45],"(ASR).This":[46],"paper":[47],"proposes":[48],"a":[49,91,97],"multi-task":[50],"training":[51,63,102],"framework":[52,142],"make":[54],"SE":[56,107,123,150,159],"unharmful":[58],"ASR.Because":[60],"ASR":[62,99,113,132,169],"samples":[64],"do":[65],"not":[66],"have":[67],"corresponding":[68],"clean":[69,85],"signal":[70,88],"references,":[71],"we":[72],"alternately":[73],"perform":[74],"two":[75,182],"model":[76,100,124],"update":[77,121,183],"steps":[78],"called":[79],"SE-step":[80],"ASR-step.The":[82],"SEstep":[83],"uses":[84],"noisy":[87],"pairs":[89],"signal-based":[92],"loss":[93,110],"function.The":[94],"ASR-step":[95],"applies":[96],"pre-trained":[98],"signals":[103],"enhanced":[104],"with":[105,127,154],"model.A":[108],"cross-entropy":[109],"between":[111],"output":[114,151],"reference":[116],"transcriptions":[117],"is":[118,162],"calculated":[119],"parameters.Experimental":[125],"results":[126],"realistic":[128],"large-scale":[129],"settings":[130],"using":[131],"trained":[134],"on":[135],"75,000-hour":[136],"data":[137,172],"show":[138],"that":[139],"proposed":[141],"improves":[143],"word":[145],"error":[146],"rate":[147],"for":[148,174],"by":[152,166],"11.82%":[153],"little":[155],"compromise":[156],"in":[157],"quality.Performance":[160],"analysis":[161],"also":[163],"carried":[164],"out":[165],"changing":[167],"model,":[170],"used":[173],"ASR-step,":[176],"schedule":[179],"steps.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}