{"id":"https://openalex.org/W4296068982","doi":"https://doi.org/10.21437/interspeech.2022-10508","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","display_name":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068982","doi":"https://doi.org/10.21437/interspeech.2022-10508"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10508","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10508","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5100809752","display_name":"Yicheng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yicheng Du","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["AIP, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIP, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouhei Sekiguchi","raw_affiliation_strings":["AIP, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIP, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["AIP, RIKEN, Japan","National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIP, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082784886","display_name":"Mathieu Fontaine","orcid":"https://orcid.org/0000-0002-7657-6271"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","AIP, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"AIP, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["AIP, RIKEN, Japan","Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIP, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07617249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2918","last_page":"2922"},"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":0.9998000264167786,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8574963212013245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7514538764953613},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.6184987425804138},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5135188698768616},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5048671364784241},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.49672919511795044},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.47466567158699036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4741111397743225},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46586063504219055},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4386428892612457},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43004846572875977},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4270450472831726},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42448678612709045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574963212013245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7514538764953613},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.6184987425804138},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5135188698768616},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5048671364784241},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.49672919511795044},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.47466567158699036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4741111397743225},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46586063504219055},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4386428892612457},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43004846572875977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4270450472831726},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42448678612709045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10508","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10508","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2101482305","display_name":"A Universal Audio Understanding Model for Localization, Separation, and Classification of Various Sounds","funder_award_id":"20K21813","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3489341541","display_name":"Audio-Visual Music Understanding Based on Integration of Recognition and Generative Processes","funder_award_id":"19H04137","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6575691015","display_name":"A Unified Computational Model for Audio-Visual Recognition of Human Social Interaction","funder_award_id":"20K19833","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1983812858","https://openalex.org/W2096653978","https://openalex.org/W2127851351","https://openalex.org/W2137048499","https://openalex.org/W2142959178","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2763188033","https://openalex.org/W2767071179","https://openalex.org/W2787692317","https://openalex.org/W2908510526","https://openalex.org/W2909607850","https://openalex.org/W2937780860","https://openalex.org/W2962784628","https://openalex.org/W2964208065","https://openalex.org/W2973179291","https://openalex.org/W3016131876","https://openalex.org/W3016230414","https://openalex.org/W3018441253","https://openalex.org/W3020336359","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3096273170","https://openalex.org/W3096338464","https://openalex.org/W3097777922","https://openalex.org/W3162358523","https://openalex.org/W3162833755","https://openalex.org/W3163464943","https://openalex.org/W3179026300","https://openalex.org/W4225320033","https://openalex.org/W4287118210","https://openalex.org/W4307435160","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"noisy":[3,136],"speech":[4,35,39,95,103,130,137,148],"recognition":[5,40,149],"for":[6],"an":[7],"augmented":[8],"reality":[9],"headset":[10],"that":[11,23,98,116,152],"helps":[12],"verbal":[13],"communication":[14],"with":[15,132,139],"in":[16,28,49],"real":[17],"multiparty":[18],"conversational":[19],"environments.A":[20],"major":[21],"approach":[22],"has":[24],"actively":[25],"been":[26],"studied":[27],"simulated":[29],"environments":[30],"is":[31],"to":[32,61,64,106],"sequentially":[33],"perform":[34],"enhancement":[36],"and":[37,70,73,122,135],"automatic":[38],"(ASR)":[41],"based":[42,91],"on":[43,92],"deep":[44],"neural":[45],"networks":[46],"(DNNs)":[47],"trained":[48],"a":[50,57,85,93,107,112],"supervised":[51],"manner.In":[52],"our":[53],"task,":[54],"however,":[55],"such":[56],"pretrained":[58],"system":[59,150],"fails":[60],"work":[62],"due":[63],"the":[65,68,74,78,82,102,119,123,145,153,158],"mismatch":[66],"between":[67],"training":[69],"test":[71],"conditions":[72],"head":[75],"movements":[76],"of":[77,84],"user.To":[79],"enhance":[80],"only":[81],"utterances":[83],"target":[86],"speaker,":[87],"we":[88],"use":[89],"beamforming":[90],"DNN-based":[94],"mask":[96,120],"estimator":[97,121],"can":[99],"adaptively":[100],"extract":[101],"components":[104],"corresponding":[105],"head-relative":[108],"particular":[109],"direction.We":[110],"propose":[111],"semi-supervised":[113],"adaptation":[114],"method":[115,155],"jointly":[117],"updates":[118],"ASR":[124,159],"model":[125],"at":[126],"run-time":[127],"using":[128,144],"clean":[129],"signals":[131,138],"ground-truth":[133],"transcriptions":[134],"highly-confident":[140],"estimated":[141],"transcriptions.Comparative":[142],"experiments":[143],"state-of-theart":[146],"distant":[147],"show":[151],"proposed":[154],"significantly":[156],"improves":[157],"performance.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}