{"id":"https://openalex.org/W4210300569","doi":"https://doi.org/10.1109/asru51503.2021.9688175","title":"ASR Rescoring and Confidence Estimation with Electra","display_name":"ASR Rescoring and Confidence Estimation with Electra","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210300569","doi":"https://doi.org/10.1109/asru51503.2021.9688175"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688175","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":"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/A5034216052","display_name":"Hayato Futami","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Futami","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"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/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"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/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8151537179946899},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6982330083847046},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6945539712905884},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6432384848594666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.627578616142273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5675621032714844},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5395249128341675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48544150590896606},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0930059552192688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151537179946899},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6982330083847046},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6945539712905884},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6432384848594666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.627578616142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675621032714844},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5395249128341675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48544150590896606},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0930059552192688},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688175","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":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1566877644","https://openalex.org/W1828163288","https://openalex.org/W2066243589","https://openalex.org/W2127141656","https://openalex.org/W2134659216","https://openalex.org/W2141354973","https://openalex.org/W2160451571","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2396464458","https://openalex.org/W2407080277","https://openalex.org/W2577366047","https://openalex.org/W2626967530","https://openalex.org/W2747917286","https://openalex.org/W2766219058","https://openalex.org/W2787642437","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2913129712","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2946375144","https://openalex.org/W2950170869","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963240019","https://openalex.org/W2965373594","https://openalex.org/W2972981900","https://openalex.org/W2979826702","https://openalex.org/W2988975212","https://openalex.org/W2990391581","https://openalex.org/W3016010032","https://openalex.org/W3016188195","https://openalex.org/W3024308166","https://openalex.org/W3026041220","https://openalex.org/W3034775979","https://openalex.org/W3034999214","https://openalex.org/W3095994005","https://openalex.org/W3097375352","https://openalex.org/W3097632072","https://openalex.org/W3097777922","https://openalex.org/W3106061119","https://openalex.org/W3119563486","https://openalex.org/W3150122400","https://openalex.org/W3151526698","https://openalex.org/W3160557590","https://openalex.org/W3160648428","https://openalex.org/W3161324588","https://openalex.org/W3161911362","https://openalex.org/W3162037819","https://openalex.org/W3163169798","https://openalex.org/W4287824654","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6691770337","https://openalex.org/W6732447497","https://openalex.org/W6739651123","https://openalex.org/W6755207826","https://openalex.org/W6758779242","https://openalex.org/W6762471145","https://openalex.org/W6766673545","https://openalex.org/W6770528390","https://openalex.org/W6771917389","https://openalex.org/W6785433122"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W1769849273","https://openalex.org/W113247760","https://openalex.org/W2132885390","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2499802997"],"abstract_inverted_index":{"In":[0,111],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"rescoring,":[5],"the":[6,9,16,34,112,155],"hypothesis":[7],"with":[8,55,165,169,173],"fewest":[10],"errors":[11,54],"should":[12],"be":[13,146],"selected":[14],"from":[15],"<tex":[17],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[18],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n$</tex>":[19],"-best":[20],"list":[21],"using":[22],"a":[23,60,121],"language":[24],"model":[25],"(LM).":[26],"However,":[27],"LMs":[28],"are":[29],"usually":[30],"trained":[31],"to":[32,41,69,95,129,189],"maximize":[33],"likelihood":[35],"of":[36,105,114],"correct":[37],"word":[38,73,117],"sequences,":[39],"not":[40,193],"detect":[42,190],"ASR":[43,48,83,96],"errors.":[44],"We":[45],"propose":[46,101],"an":[47,102],"rescoring":[49,136,163,171],"method":[50,62,137,164],"for":[51,63,140,148],"directly":[52],"detecting":[53,141],"ELECTRA,":[56],"which":[57,80,125],"is":[58,67,74,118,138,167],"originally":[59],"pre-training":[61,93,113],"NLP":[64],"tasks.":[65],"ELECTRA":[66,106,109,166,176],"pre-trained":[68],"predict":[70],"whether":[71],"each":[72,116],"replaced":[75,119],"by":[76,120],"BERT":[77,184],"or":[78],"not,":[79],"can":[81,144,187],"simulate":[82],"error":[84,97],"detection":[85],"on":[86,154],"large":[87],"text":[88],"corpora.":[89],"To":[90],"make":[91],"this":[92],"closer":[94],"detection,":[98],"we":[99],"further":[100],"extended":[103],"version":[104],"called":[107],"phone-attentive":[108],"(P-ELECTRA).":[110],"P-ELECTRA,":[115],"phone-to-word":[122],"conversion":[123],"model,":[124],"leverages":[126],"phone":[127],"information":[128],"generate":[130],"acoustically":[131],"similar":[132],"words.":[133],"Since":[134],"our":[135,162],"optimized":[139],"errors,":[142],"it":[143,186],"also":[145,177,198],"used":[147],"word-level":[149],"confidence":[150,181],"estimation.":[151],"Experimental":[152],"evaluations":[153],"Librispeech":[156],"and":[157],"TED-LIUM2":[158],"corpora":[159],"show":[160],"that":[161],"competitive":[168],"conventional":[170],"methods":[172],"faster":[174],"inference.":[175],"performs":[178],"better":[179],"in":[180,195,199],"estimation":[182],"than":[183],"because":[185],"learn":[188],"inappropriate":[191],"words":[192],"only":[194],"fine-tuning":[196],"but":[197],"pre-training.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}