{"id":"https://openalex.org/W4297841613","doi":"https://doi.org/10.21437/interspeech.2022-11177","title":"ASR Error Detection via Audio-Transcript entailment","display_name":"ASR Error Detection via Audio-Transcript entailment","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841613","doi":"https://doi.org/10.21437/interspeech.2022-11177"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11177","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":"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/A5026622857","display_name":"Nimshi Venkat Meripo","orcid":null},"institutions":[{"id":"https://openalex.org/I2800797889","display_name":"Northridge Hospital Medical Center","ror":"https://ror.org/0082w0p19","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800797889","https://openalex.org/I2802827176"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nimshi Venkat Meripo","raw_affiliation_strings":["Abridge AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abridge AI Inc","institution_ids":["https://openalex.org/I2800797889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018965013","display_name":"Sandeep Konam","orcid":null},"institutions":[{"id":"https://openalex.org/I2800797889","display_name":"Northridge Hospital Medical Center","ror":"https://ror.org/0082w0p19","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800797889","https://openalex.org/I2802827176"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Konam","raw_affiliation_strings":["Abridge AI Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abridge AI Inc","institution_ids":["https://openalex.org/I2800797889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800797889"],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55274294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3358","last_page":"3362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9843000173568726,"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":0.9843000173568726,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9815999865531921,"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":0.7002444267272949},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.6068001985549927},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.5460067987442017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5343465209007263},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44982168078422546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35830551385879517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002444267272949},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.6068001985549927},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.5460067987442017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5343465209007263},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44982168078422546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35830551385879517}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11177","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W21942408","https://openalex.org/W138612281","https://openalex.org/W191484614","https://openalex.org/W2034537249","https://openalex.org/W2084294137","https://openalex.org/W2103622292","https://openalex.org/W2407634150","https://openalex.org/W2797303992","https://openalex.org/W2883191466","https://openalex.org/W2896457183","https://openalex.org/W2901265786","https://openalex.org/W2905024391","https://openalex.org/W2913566369","https://openalex.org/W2966690051","https://openalex.org/W2984982467","https://openalex.org/W3016256870","https://openalex.org/W3023363161","https://openalex.org/W3034503989","https://openalex.org/W3036601975","https://openalex.org/W3046177490","https://openalex.org/W3097314730","https://openalex.org/W3102662787","https://openalex.org/W3103410128","https://openalex.org/W3169320628","https://openalex.org/W3172899477","https://openalex.org/W3177464472","https://openalex.org/W4251486063","https://openalex.org/W4287996124","https://openalex.org/W4297799160","https://openalex.org/W4385572941"],"related_works":["https://openalex.org/W2118335617","https://openalex.org/W2053800966","https://openalex.org/W2296063830","https://openalex.org/W1997269821","https://openalex.org/W1987976971","https://openalex.org/W2795227599","https://openalex.org/W192785878","https://openalex.org/W2911667057","https://openalex.org/W131127834","https://openalex.org/W187730917"],"abstract_inverted_index":{"Despite":[0],"improved":[1],"performances":[2],"of":[3,68,134,165],"the":[4,66,73,85,127,141],"latest":[5],"Automatic":[6],"Speech":[7],"Recognition":[8],"(ASR)":[9],"systems,":[10],"transcription":[11,169],"errors":[12,16,37,170,175],"are":[13,72,137,145],"still":[14],"unavoidable.These":[15],"can":[17],"have":[18],"a":[19,39,55,99,122,150,181],"considerable":[20],"impact":[21],"in":[22,43,147],"critical":[23,40],"domains":[24],"such":[25],"as":[26,79],"healthcare,":[27],"when":[28,106],"used":[29,146],"to":[30,48,75,125,139,178],"help":[31],"with":[32],"clinical":[33],"documentation.Therefore,":[34],"detecting":[35],"ASR":[36,60],"is":[38,94,108,153],"first":[41,74],"step":[42],"preventing":[44],"further":[45],"error":[46,61,111,162],"propagation":[47],"downstream":[49],"applications.To":[50],"this":[51,77],"end,":[52],"we":[53,71],"propose":[54],"novel":[56],"end-to-end":[57,81],"approach":[58],"for":[59],"detection":[62],"using":[63],"audio-transcript":[64],"entailment.To":[65],"best":[67],"our":[69,148],"knowledge,":[70],"frame":[76],"problem":[78],"an":[80,118],"entailment":[82,101],"task":[83],"between":[84,102],"audio":[86,103],"segment":[87],"and":[88,104,112,121,129,171,186],"its":[89],"corresponding":[90],"transcript":[91,105,130],"segment.Our":[92],"intuition":[93],"that":[95],"there":[96,107],"should":[97],"be":[98],"bidirectional":[100],"no":[109],"recognition":[110],"vice":[113],"versa.The":[114],"proposed":[115,158],"model":[116,126,159],"utilizes":[117],"acoustic":[119],"encoder":[120,124],"linguistic":[123],"speech":[128],"respectively.The":[131],"encoded":[132],"representations":[133],"both":[135],"modalities":[136],"fused":[138],"predict":[140],"entailment.Since":[142],"doctor-patient":[143],"conversations":[144],"experiments,":[149],"particular":[151],"emphasis":[152],"placed":[154],"on":[155,167,173],"medical":[156,174],"terms.Our":[157],"achieves":[160],"classification":[161],"rates":[163],"(CER)":[164],"26.2%":[166],"all":[168],"23%":[172],"specifically,":[176],"leading":[177],"improvements":[179],"upon":[180],"strong":[182],"baseline":[183],"by":[184],"12%":[185],"15.4%,":[187],"respectively.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}