{"id":"https://openalex.org/W4408353737","doi":"https://doi.org/10.1109/icassp49660.2025.10890057","title":"Contextual ASR with Retrieval Augmented Large Language Model","display_name":"Contextual ASR with Retrieval Augmented Large Language Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353737","doi":"https://doi.org/10.1109/icassp49660.2025.10890057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890057","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/A5101215727","display_name":"Cihan Xiao","orcid":"https://orcid.org/0009-0006-6262-3213"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cihan Xiao","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055234106","display_name":"Zejiang Hou","orcid":"https://orcid.org/0000-0002-6836-8288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejiang Hou","raw_affiliation_strings":["AWS AI Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["AWS AI Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyu J Han","raw_affiliation_strings":["AWS AI Labs,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI Labs,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85579118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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/T10028","display_name":"Topic Modeling","score":0.9799000024795532,"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/T10028","display_name":"Topic Modeling","score":0.9799000024795532,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9319999814033508,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9235000014305115,"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":0.8439556956291199},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6162583231925964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49345913529396057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40808072686195374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3770074248313904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439556956291199},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6162583231925964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49345913529396057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40808072686195374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3770074248313904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890057","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3119308075","https://openalex.org/W3197674197","https://openalex.org/W4389519450","https://openalex.org/W4391021623","https://openalex.org/W4392902876","https://openalex.org/W4392903078","https://openalex.org/W4392903956","https://openalex.org/W4402111737","https://openalex.org/W4402111987","https://openalex.org/W4406461487","https://openalex.org/W6600880057","https://openalex.org/W6776148200","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6858023062","https://openalex.org/W6859099255","https://openalex.org/W6861295083","https://openalex.org/W6866575372","https://openalex.org/W6869734748"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2,13],"(ASR)":[3],"systems":[4,80],"can":[5],"benefit":[6],"from":[7],"incorporating":[8],"contextual":[9,34,48,72,89],"information":[10],"to":[11,37,69,87,124,129],"improve":[12],"accuracy,":[14],"especially":[15],"for":[16],"uncommon":[17],"words":[18],"or":[19,26],"phrases.":[20],"Current":[21],"approaches":[22],"like":[23],"custom":[24,110],"vocabularies":[25],"prompting":[27],"with":[28,92],"previous":[29],"transcript":[30],"segments":[31],"provide":[32],"limited":[33],"control.":[35],"Compared":[36],"existing":[38],"context":[39,93,128],"biasing":[40],"methods,":[41],"RAG":[42],"promises":[43],"more":[44],"flexible":[45],"and":[46,65,84,107],"scalable":[47],"control":[49],"by":[50,95],"leveraging":[51,60],"LLMs\u2019":[52],"broad":[53],"knowledge.":[54],"To":[55],"this":[56],"end,":[57],"we":[58,78],"propose":[59,79],"large":[61],"language":[62],"models":[63],"(LLMs)":[64],"retrieval-augmented":[66],"generation":[67],"(RAG)":[68],"enhance":[70],"the":[71,101,118,126],"capabilities":[73],"of":[74],"ASR":[75,102,105],"systems.":[76],"Specifically,":[77],"based":[81],"on":[82],"text":[83],"audio":[85],"LLMs":[86],"perform":[88,130],"error":[90,131],"correction":[91,132],"retrieved":[94],"querying":[96],"a":[97,108],"text-based":[98],"retriever":[99],"using":[100],"module\u2019s":[103],"firstpass":[104],"hypotheses":[106],"frequency-based":[109],"vocabulary":[111],"(CV)":[112],"list.":[113],"Our":[114],"experiments":[115],"reveal":[116],"that":[117],"fine-tuned":[119],"system":[120],"has":[121],"effectively":[122],"learned":[123],"extract":[125],"relevant":[127],"while":[133],"maintaining":[134],"robustness":[135],"against":[136],"noise.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}