{"id":"https://openalex.org/W7148463928","doi":"https://doi.org/10.1109/asru65441.2025.11434757","title":"Customizing Speech Recognition Model with Large Language Model Feedback","display_name":"Customizing Speech Recognition Model with Large Language Model Feedback","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148463928","doi":"https://doi.org/10.1109/asru65441.2025.11434757"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5109397773","display_name":"Shaoshi Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaoshi Ling","raw_affiliation_strings":["Microsoft Core AI,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Core AI,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807397","display_name":"Guoli Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoli Ye","raw_affiliation_strings":["Microsoft Core AI,Redmond,WA,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Core AI,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109397773"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92937467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8884000182151794,"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":0.8884000182151794,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01590000092983246,"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":0.015599999576807022,"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/language-model","display_name":"Language model","score":0.7235000133514404},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.710099995136261},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.657800018787384},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4487999975681305},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3549000024795532},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3231000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116000294685364},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7235000133514404},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.710099995136261},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580000281333923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5164999961853027},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":25,"referenced_works":["https://openalex.org/W2122922389","https://openalex.org/W2587088898","https://openalex.org/W2936252403","https://openalex.org/W2962894366","https://openalex.org/W2963057973","https://openalex.org/W2963122170","https://openalex.org/W2963144852","https://openalex.org/W2963796169","https://openalex.org/W3112702554","https://openalex.org/W3163169798","https://openalex.org/W3163464943","https://openalex.org/W3198587774","https://openalex.org/W3202037040","https://openalex.org/W3205080563","https://openalex.org/W3211278025","https://openalex.org/W4223945715","https://openalex.org/W4372259777","https://openalex.org/W4372269772","https://openalex.org/W4385656656","https://openalex.org/W4389518985","https://openalex.org/W4389799542","https://openalex.org/W4408565363","https://openalex.org/W4415798390","https://openalex.org/W7131800114","https://openalex.org/W7133208539"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"systems":[4],"have":[5],"achieved":[6],"strong":[7],"performance":[8],"on":[9,35,121],"general":[10],"transcription":[11,68],"tasks.":[12],"However,":[13],"they":[14],"continue":[15],"to":[16,25,66,93,107],"struggle":[17],"with":[18],"recognizing":[19],"rare":[20],"named":[21,71],"entities":[22,72],"and":[23],"adapting":[24],"domain":[26,61,75],"mismatches.":[27],"In":[28,49],"contrast,":[29],"large":[30],"language":[31],"models":[32],"(LLMs),":[33],"trained":[34],"massive":[36],"internet-scale":[37],"datasets,":[38],"are":[39],"often":[40],"more":[41],"effective":[42],"across":[43],"a":[44,54,79,87,118],"wide":[45],"range":[46],"of":[47],"domains.":[48],"this":[50],"work,":[51],"we":[52],"propose":[53],"reinforcement":[55,113],"learning":[56],"based":[57],"approach":[58],"for":[59],"unsupervised":[60],"adaptation,":[62],"leveraging":[63],"unlabeled":[64],"data":[65],"enhance":[67],"quality\u2014particularly":[69],"the":[70,90,95,98,109],"affected":[73],"by":[74],"mismatch\u2014through":[76],"feedback":[77],"from":[78,97],"LLM.":[80],"Given":[81],"contextual":[82],"information,":[83],"our":[84],"framework":[85],"employs":[86],"LLM":[88],"as":[89,104],"reward":[91,105],"model":[92,111],"score":[94],"hypotheses":[96],"ASR":[99,110],"model.":[100],"These":[101],"scores":[102],"serve":[103],"signals":[106],"fine-tune":[108],"via":[112],"learning.":[114],"Our":[115],"method":[116],"achieves":[117],"21%":[119],"improvement":[120],"entity":[122],"word":[123],"error":[124],"rate":[125],"over":[126],"conventional":[127],"self-training":[128],"methods.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}