{"id":"https://openalex.org/W4408345625","doi":"https://doi.org/10.1109/icassp49660.2025.10888936","title":"Retrieval Augmented Correction of Named Entity Speech Recognition Errors","display_name":"Retrieval Augmented Correction of Named Entity Speech Recognition Errors","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345625","doi":"https://doi.org/10.1109/icassp49660.2025.10888936"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5048094198","display_name":"Ernest Pusateri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ernest Pusateri","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065974400","display_name":"Anmol Walia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anmol Walia","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040858416","display_name":"Anirudh Kashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anirudh Kashi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023057939","display_name":"Bortik Bandyopadhyay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bortik Bandyopadhyay","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nadia Hyder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nadia Hyder","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056602829","display_name":"Sayantan Mahinder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sayantan Mahinder","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061951248","display_name":"Raviteja Anantha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Raviteja Anantha","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069329694","display_name":"Daben Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daben Liu","raw_affiliation_strings":["Capital One"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital One","institution_ids":["https://openalex.org/I1305444813"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091396390","display_name":"Sashank Gondala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sashank Gondala","raw_affiliation_strings":["Further AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Further AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94722991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9797000288963318,"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":0.9797000288963318,"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":0.9768000245094299,"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":0.9473999738693237,"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":0.7945476770401001},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.652572512626648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5827760696411133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382245779037476},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5176292061805725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3336982727050781},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.06508490443229675},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05683097243309021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945476770401001},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.652572512626648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5827760696411133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382245779037476},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5176292061805725},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336982727050781},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.06508490443229675},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05683097243309021},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2916997151","https://openalex.org/W2970671861","https://openalex.org/W3093312917","https://openalex.org/W3194782062","https://openalex.org/W4210684870","https://openalex.org/W4221167707","https://openalex.org/W4296068409","https://openalex.org/W4319862713","https://openalex.org/W4367189587","https://openalex.org/W4372347689","https://openalex.org/W4388017359","https://openalex.org/W4391021736","https://openalex.org/W4391093289","https://openalex.org/W4392902876","https://openalex.org/W4392903347","https://openalex.org/W4402111608","https://openalex.org/W6746052068","https://openalex.org/W6780899003","https://openalex.org/W6796581206","https://openalex.org/W6845404407","https://openalex.org/W6846966473","https://openalex.org/W6850625674","https://openalex.org/W6854445763","https://openalex.org/W6868695479"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3204019825","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650","https://openalex.org/W2287770975"],"abstract_inverted_index":{"In":[0,35,62,85],"recent":[1],"years,":[2],"end-to-end":[3,41],"automatic":[4],"speech":[5,95],"recognition":[6,96],"(ASR)":[7],"systems":[8,18],"have":[9,20,48],"proven":[10,49],"themselves":[11],"remarkably":[12],"accurate":[13],"and":[14,125],"performant,":[15],"but":[16],"these":[17,130],"still":[19],"a":[21,52,66,90,103,108,181],"significant":[22],"error":[23,158],"rate":[24,159],"for":[25,55,93],"entity":[26,97],"names":[27],"which":[28,142],"appear":[29],"infrequently":[30],"in":[31],"their":[32],"training":[33],"data.":[34],"parallel":[36],"to":[37,50,106,139,146],"the":[38,126,136,177],"rise":[39],"of":[40,68,110,170],"ASR":[42,123,137,148],"systems,":[43],"large":[44],"language":[45,58],"models":[46],"(LLMs)":[47],"be":[51],"versatile":[53],"tool":[54],"various":[56],"natural":[57],"processing":[59],"(NLP)":[60],"tasks.":[61],"NLP":[63],"tasks":[64],"where":[65],"database":[67,105,115],"relevant":[69,111],"knowledge":[70],"is":[71],"available,":[72],"retrieval":[73],"augmented":[74],"generation":[75],"(RAG)":[76],"has":[77,143],"achieved":[78],"impressive":[79],"results":[80],"when":[81],"used":[82],"with":[83,135],"LLMs.":[84],"this":[86],"work,":[87],"we":[88],"propose":[89],"RAG-like":[91],"technique":[92],"correcting":[94],"name":[98],"errors.":[99,149],"Our":[100],"approach":[101],"uses":[102],"vector":[104],"index":[107],"set":[109,187],"entities.":[112],"At":[113],"runtime,":[114],"queries":[116,131,169],"are":[117,132],"generated":[118],"from":[119],"possibly":[120],"errorful":[121],"textual":[122],"hypotheses,":[124,138],"entities":[127,173],"retrieved":[128],"using":[129],"fed,":[133],"along":[134],"an":[140],"LLM":[141],"been":[144],"adapted":[145],"correct":[147],"Overall,":[150],"our":[151],"best":[152],"system":[153],"achieves":[154],"33%-39%":[155],"relative":[156],"word":[157],"reductions":[160],"on":[161,166,176],"synthetic":[162],"test":[163,179,186],"sets":[164],"focused":[165],"voice":[167,184],"assistant":[168,185],"rare":[171],"music":[172],"without":[174],"regressing":[175],"STOP":[178],"set,":[180],"publicly":[182],"available":[183],"covering":[188],"many":[189],"domains.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}