{"id":"https://openalex.org/W4388821450","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317247","title":"Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture","display_name":"Flexible Evidence Model to Reduce Uncertainty Mismatch Between Speech Enhancement and ASR Based on Encoder-Decoder Architecture","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821450","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317247"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5018403421","display_name":"Ryu Takeda","orcid":"https://orcid.org/0009-0007-0518-6245"},"institutions":[{"id":"https://openalex.org/I4210110027","display_name":"Sanken Electric (Japan)","ror":"https://ror.org/01v07hj96","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110027"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryu Takeda","raw_affiliation_strings":["Osaka University,SANKEN,Japan","SANKEN, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,SANKEN,Japan","institution_ids":["https://openalex.org/I4210110027","https://openalex.org/I98285908"]},{"raw_affiliation_string":"SANKEN, Osaka University, Japan","institution_ids":["https://openalex.org/I4210110027","https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Honda Research Institute Japan, Co., Ltd.,Japan","Honda Research Institute Japan, Co., Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan, Co., Ltd.,Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co., Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I4210110027","display_name":"Sanken Electric (Japan)","ror":"https://ror.org/01v07hj96","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110027"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Osaka University,SANKEN,Japan","SANKEN, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,SANKEN,Japan","institution_ids":["https://openalex.org/I4210110027","https://openalex.org/I98285908"]},{"raw_affiliation_string":"SANKEN, Osaka University, Japan","institution_ids":["https://openalex.org/I4210110027","https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65506995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1830","last_page":"1837"},"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.7948606014251709},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.764305591583252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6635597348213196},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6243762969970703},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4994528293609619},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49791765213012695},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46437233686447144},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.435314416885376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38053029775619507},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08721548318862915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948606014251709},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.764305591583252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6635597348213196},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6243762969970703},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4994528293609619},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49791765213012695},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46437233686447144},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.435314416885376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38053029775619507},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08721548318862915},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W168469469","https://openalex.org/W1485014097","https://openalex.org/W1974972740","https://openalex.org/W2020934227","https://openalex.org/W2074354966","https://openalex.org/W2110873266","https://openalex.org/W2130363011","https://openalex.org/W2148719987","https://openalex.org/W2171992722","https://openalex.org/W2327501763","https://openalex.org/W2399335961","https://openalex.org/W2547288128","https://openalex.org/W2584063687","https://openalex.org/W2606436965","https://openalex.org/W2683320792","https://openalex.org/W2729166723","https://openalex.org/W2766219058","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2972541922","https://openalex.org/W2998657200","https://openalex.org/W3097777922","https://openalex.org/W3151851237","https://openalex.org/W4293363567","https://openalex.org/W4297841730","https://openalex.org/W4311000453","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6638545294","https://openalex.org/W6640963894","https://openalex.org/W6766978945","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2494523064","https://openalex.org/W2401089611","https://openalex.org/W3211091508","https://openalex.org/W2136586452","https://openalex.org/W68492818"],"abstract_inverted_index":{"Missing-data":[0],"automatic":[1],"speech":[2,10,62,73],"recognition":[3,89],"(ASR)":[4],"can":[5,113],"use":[6],"the":[7,32,44,54,70,100,115,129,135,146],"uncertainty":[8,21,67,78,117],"of":[9,43,72],"enhancement":[11],"(SE)":[12],"results":[13],"to":[14,56,98,107],"improve":[15],"ASR":[16,45,85,130,153],"performance":[17],"without":[18],"joint-training.":[19],"Such":[20],"is":[22],"represented":[23],"by":[24,122,140],"a":[25,39,83,94,151,156],"probabilistic":[26],"evidence":[27,35,96],"model,":[28,46,86],"whose":[29],"design":[30],"affects":[31],"performance.":[33],"Previous":[34],"models":[36],"have":[37],"utilized":[38],"specific":[40],"distribution":[41,110],"regardless":[42],"and":[47,60,82,112],"do":[48],"not":[49],"consider":[50],"their":[51],"robustness,":[52],"i.e.,":[53],"ability":[55],"recognize":[57],"both":[58],"clean":[59],"noisy":[61],"(robust":[63],"ASR).":[64],"The":[65],"SE":[66,81,116],"depends":[68],"on":[69],"degree":[71],"cleanness,":[74],"which":[75],"causes":[76],"an":[77,119],"mismatch":[79],"between":[80],"robust":[84,152],"resulting":[87],"in":[88,126],"failures.":[90],"We":[91],"thus":[92],"propose":[93],"flexible":[95],"model":[97,103,154],"reduce":[99],"mismatch.":[101],"Our":[102],"features":[104],"several":[105],"parameters":[106,125],"control":[108],"its":[109],"shape":[111],"reweight":[114],"via":[118],"encoder-decoder":[120],"architecture":[121],"automatically":[123],"selecting":[124],"accordance":[127],"with":[128,150],"scores.":[131],"Experiments":[132],"showed":[133],"that":[134],"character":[136],"error":[137],"rate":[138],"improved":[139],"more":[141],"than":[142],"3":[143],"points":[144],"over":[145],"best":[147],"baseline":[148],"even":[149],"under":[155],"\u22125-dB":[157],"SNR":[158],"condition.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}