{"id":"https://openalex.org/W7148523712","doi":"https://doi.org/10.1109/asru65441.2025.11434775","title":"Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction","display_name":"Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148523712","doi":"https://doi.org/10.1109/asru65441.2025.11434775"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434775","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/A5109489201","display_name":"Y. Y. Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangui Fang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Baixu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baixu Chen","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132798318","display_name":"Jing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Peng","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800912","display_name":"Xu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801627","display_name":"Yu Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767831","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0003-1620-4510"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101083815","display_name":"Guohui Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohui Zhong","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109489201"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86873566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.42500001192092896,"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":0.42500001192092896,"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":0.1128000020980835,"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":0.09929999709129333,"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/correctness","display_name":"Correctness","score":0.7529000043869019},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.7116000056266785},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6166999936103821},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.33219999074935913},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.7116000056266785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980999708175659},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.531000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.2777999937534332}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434775","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4704638123512268}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2507739667","https://openalex.org/W2785918467","https://openalex.org/W2860591049","https://openalex.org/W2963026768","https://openalex.org/W2963242190","https://openalex.org/W3016256870","https://openalex.org/W3093312917","https://openalex.org/W3197478142","https://openalex.org/W3202576380","https://openalex.org/W3207553988","https://openalex.org/W4382202529","https://openalex.org/W4385573332","https://openalex.org/W4389010951","https://openalex.org/W4391021773","https://openalex.org/W4404781799","https://openalex.org/W4408565363"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"error":[4,70],"correction":[5,107],"aims":[6],"to":[7,45],"correct":[8,50],"recognition":[9],"errors":[10],"while":[11],"preserving":[12],"accurate":[13],"text.":[14,51],"Although":[15],"traditional":[16],"approaches":[17],"demonstrate":[18],"moderate":[19],"effectiveness,":[20],"LLMs":[21,37],"offer":[22],"a":[23],"paradigm":[24],"that":[25,88,118],"eliminates":[26],"the":[27,46,49,58,98,102,105,119],"need":[28],"for":[29],"training":[30],"and":[31,77,100,115,133],"labeled":[32],"data.":[33],"However,":[34],"directly":[35],"using":[36],"will":[38],"encounter":[39],"hallucinations":[40],"problem,":[41,55],"which":[42,64],"may":[43],"lead":[44],"modification":[47],"of":[48,66,84,97,104],"To":[52],"address":[53],"this":[54],"we":[56],"propose":[57],"Reliable":[59],"LLM":[60,106],"Correction":[61],"Framework":[62],"(RLLMCF),":[63],"consists":[65],"three":[67],"stages:":[68],"(1)":[69],"pre-detection,":[71],"(2)":[72],"chain-of-thought":[73],"sub-tasks":[74],"iterative":[75],"correction,":[76],"(3)":[78],"reasoning":[79],"process":[80],"verification.":[81],"The":[82],"advantage":[83],"our":[85,124],"method":[86],"is":[87],"it":[89],"does":[90],"not":[91],"require":[92],"additional":[93],"information":[94],"or":[95],"fine-tuning":[96],"model,":[99],"ensures":[101],"correctness":[103],"under":[108],"multipass":[109],"programming.":[110],"Experiments":[111],"on":[112],"AISHELL-1,":[113],"AISHELL-2,":[114],"Librispeech":[116],"show":[117],"GPT-4o":[120],"model":[121],"enhanced":[122],"by":[123],"framework":[125],"achieves":[126],"$21":[127],"\\%,":[128,130],"11":[129],"9":[131],"\\%$,":[132],"$11.4":[134],"\\%$":[135],"relative":[136],"reductions":[137],"in":[138],"CER/WER.":[139]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2026-04-03T00:00:00"}
