{"id":"https://openalex.org/W4408352893","doi":"https://doi.org/10.1109/icassp49660.2025.10888744","title":"Contextualization of ASR with LLM using phonetic retrieval-based augmentation","display_name":"Contextualization of ASR with LLM using phonetic retrieval-based augmentation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352893","doi":"https://doi.org/10.1109/icassp49660.2025.10888744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888744","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/A5040740925","display_name":"Zhihong Lei","orcid":"https://orcid.org/0000-0001-7846-3417"},"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":true,"raw_author_name":"Zhihong Lei","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012173647","display_name":"Xingyu Na","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":"Xingyu Na","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086280874","display_name":"Mingbin Xu","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":"Mingbin Xu","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084609544","display_name":"C Gysel","orcid":"https://orcid.org/0000-0003-3433-7317"},"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":"Christophe Van Gysel","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599805","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0003-0557-9296"},"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":"Yuanyuan Zhang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054574376","display_name":"Shiyi Han","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":"Shiyi Han","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011008665","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0003-4819-373X"},"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":"Zhen Huang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5040740925"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":5.7199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94906812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9871000051498413,"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":0.9871000051498413,"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":0.9409000277519226,"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/T12031","display_name":"Speech and dialogue systems","score":0.9257000088691711,"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/contextualization","display_name":"Contextualization","score":0.9437799453735352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063241243362427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6150636672973633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.508988618850708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5057041645050049},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36290109157562256},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12971630692481995}],"concepts":[{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.9437799453735352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063241243362427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6150636672973633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.508988618850708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5057041645050049},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36290109157562256},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12971630692481995},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888744","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","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2886319145","https://openalex.org/W3097777922","https://openalex.org/W4385822970","https://openalex.org/W4389518985","https://openalex.org/W4391021736","https://openalex.org/W4392903288","https://openalex.org/W4392903347","https://openalex.org/W4392903872","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4401042959","https://openalex.org/W4402670040","https://openalex.org/W6777615688","https://openalex.org/W6796581206","https://openalex.org/W6853998256","https://openalex.org/W6857131320","https://openalex.org/W6858023062"],"related_works":["https://openalex.org/W1687432146","https://openalex.org/W1591874556","https://openalex.org/W2185608106","https://openalex.org/W3046258185","https://openalex.org/W1548083239","https://openalex.org/W3216994056","https://openalex.org/W2268232908","https://openalex.org/W2146570735","https://openalex.org/W205610463","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"superb":[6],"capability":[7],"of":[8],"modeling":[9],"multimodal":[10],"signals":[11],"including":[12],"audio":[13],"and":[14,65,105,111,133,167],"text,":[15],"allowing":[16],"the":[17,35,50,72,77,109,155,158],"model":[18,36],"to":[19,37,70,95,108,126,142,169],"generate":[20],"spoken":[21],"or":[22],"textual":[23],"response":[24],"given":[25],"a":[26,32,46,61,67,93,102,118,143],"speech":[27,62,83],"input.":[28],"However,":[29],"it":[30,164],"remains":[31],"challenge":[33],"for":[34],"recognize":[38],"personal":[39,103],"named":[40,80,90,99,136,160,171],"entities,":[41],"such":[42],"as":[43,92],"contacts":[44],"in":[45,82],"phone":[47],"book,":[48],"when":[49],"input":[51],"modality":[52],"is":[53],"speech.":[54],"In":[55,117],"this":[56,89],"work,":[57],"we":[58,74],"start":[59],"with":[60,157],"recognition":[63],"task":[64],"propose":[66],"retrievalbased":[68],"solution":[69,123,150],"contextualize":[71],"LLM:":[73],"first":[75],"let":[76],"LLM":[78,115,156],"detect":[79],"entities":[81,100],"without":[84,146],"any":[85],"context,":[86],"then":[87],"use":[88],"entity":[91,137,161,172],"query":[94],"retrieve":[96],"phonetically":[97],"similar":[98],"from":[101],"database":[104],"feed":[106],"them":[107],"LLM,":[110],"finally":[112],"run":[113],"context-aware":[114],"decoding.":[116],"voice":[119],"assistant":[120],"task,":[121],"our":[122,149],"achieved":[124],"up":[125],"30.2%":[127],"relative":[128,135],"word":[129],"error":[130,138],"rate":[131,139],"reduction":[132,140],"73.6%":[134],"compared":[141],"baseline":[144],"system":[145],"contextualization.":[147],"Notably,":[148],"by":[151],"design":[152],"avoids":[153],"prompting":[154],"full":[159],"database,":[162],"making":[163],"highly":[165],"efficient":[166],"applicable":[168],"large":[170],"databases.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}