{"id":"https://openalex.org/W4391021457","doi":"https://doi.org/10.1109/asru57964.2023.10389732","title":"Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition","display_name":"Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021457","doi":"https://doi.org/10.1109/asru57964.2023.10389732"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5032504077","display_name":"Yuang Li","orcid":"https://orcid.org/0000-0002-2244-0184"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuang Li","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709477","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-5715-3011"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9369,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9291501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9986000061035156,"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":0.9943000078201294,"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":0.8665297627449036},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7216520309448242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6787800192832947},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6595233678817749},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.651067852973938},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6106795072555542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5594190955162048},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5527292490005493},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5375397205352783},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.524493396282196},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4262322783470154},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42224615812301636},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4190284013748169},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15245208144187927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06251278519630432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665297627449036},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7216520309448242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6787800192832947},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6595233678817749},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.651067852973938},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6106795072555542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594190955162048},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5527292490005493},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5375397205352783},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.524493396282196},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4262322783470154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42224615812301636},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4190284013748169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15245208144187927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06251278519630432},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389732","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389732","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1915251500","https://openalex.org/W2127141656","https://openalex.org/W2250357346","https://openalex.org/W2888779557","https://openalex.org/W2936774411","https://openalex.org/W2963240019","https://openalex.org/W2964110616","https://openalex.org/W2995181338","https://openalex.org/W3008037978","https://openalex.org/W3016234571","https://openalex.org/W3143186397","https://openalex.org/W3152221657","https://openalex.org/W3163560333","https://openalex.org/W3173051858","https://openalex.org/W3174770825","https://openalex.org/W3186813771","https://openalex.org/W3197688480","https://openalex.org/W3198587774","https://openalex.org/W3202419788","https://openalex.org/W3205788551","https://openalex.org/W3209059054","https://openalex.org/W3211278025","https://openalex.org/W4225808286","https://openalex.org/W4283031490","https://openalex.org/W4296068796","https://openalex.org/W4311000453","https://openalex.org/W4322718191","https://openalex.org/W4361229539","https://openalex.org/W4366850747","https://openalex.org/W4372266510","https://openalex.org/W4375869444","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6691509046","https://openalex.org/W6757817989","https://openalex.org/W6778883912","https://openalex.org/W6802564859","https://openalex.org/W6810334672","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6851948999","https://openalex.org/W6851950068"],"related_works":["https://openalex.org/W50892825","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,28,36,79,94,130,133],"Language":[3],"Models":[4],"(LMs)":[5],"has":[6,127],"proven":[7],"to":[8,13],"be":[9],"an":[10,95],"effective":[11],"way":[12],"address":[14],"domain":[15,30,56,106],"shifts":[16],"in":[17,42,70],"speech":[18],"recognition.":[19],"However,":[20],"these":[21,40],"approaches":[22],"usually":[23],"require":[24],"a":[25,47,61,80],"significant":[26],"amount":[27],"target":[29],"text":[31,49],"data":[32],"for":[33],"the":[34,92,124,128],"training":[35],"LMs.":[37],"Different":[38],"from":[39],"methods,":[41],"this":[43],"work,":[44],"with":[45,84,103],"only":[46,104],"domain-specific":[48],"prompt,":[50,107],"we":[51],"propose":[52],"two":[53,71],"zero-shot":[54],"ASR":[55,82,98],"adaptation":[57],"methods":[58,109],"using":[59],"LLaMA,":[60],"7-billionparameter":[62],"large":[63],"language":[64],"model":[65],"(LLM).":[66],"LLM":[67,90],"is":[68],"used":[69],"ways:":[72],"1)":[73],"second-pass":[74],"rescoring:":[75],"reranking":[76],"N-best":[77],"hypotheses":[78],"given":[81],"system":[83],"LLaMA;":[85],"2)":[86],"deep":[87,125],"LLM-fusion:":[88],"incorporating":[89],"into":[91],"decoder":[93],"encoder-decoder":[96],"based":[97],"system.":[99],"Experiments":[100],"show":[101],"that,":[102],"one":[105],"both":[108],"can":[110],"effectively":[111],"reduce":[112],"word":[113],"error":[114],"rates":[115],"(WER)":[116],"on":[117],"out-of-domain":[118],"TedLium-2":[119],"and":[120,135],"SPGISpeech":[121],"datasets.":[122],"Especially,":[123],"LLM-fusion":[126],"advantage":[129],"better":[131],"recall":[132],"entity":[134],"out-of-vocabulary":[136],"words.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}