{"id":"https://openalex.org/W4416799538","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249374","title":"Chain-of-Thought Distillation for ASR Error Correction with Multimodal Large Language Models","display_name":"Chain-of-Thought Distillation for ASR Error Correction with Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799538","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249374"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5031205975","display_name":"So\u2010Young Yang","orcid":"https://orcid.org/0000-0002-6850-3486"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaomeng Yang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029740891","display_name":"Jiaming Luo","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":"Jiaming Luo","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024002297","display_name":"Jinran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinran Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103006844","display_name":"Yongjie Zhou","orcid":"https://orcid.org/0000-0001-6384-2684"},"institutions":[{"id":"https://openalex.org/I4210119375","display_name":"Shenzhen KangNing Hospital","ror":"https://ror.org/02skpkw64","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210119375"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjie Zhou","raw_affiliation_strings":["Shenzhen Kangning Hospital,Shenzhen, Guangdong,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Kangning Hospital,Shenzhen, Guangdong,China","institution_ids":["https://openalex.org/I4210119375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824295","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0001-7241-290X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062053942","display_name":"Nan Yan","orcid":"https://orcid.org/0000-0002-1613-9301"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031205975"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19469258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7063999772071838,"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":0.7063999772071838,"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":0.038100000470876694,"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":0.03449999913573265,"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/distillation","display_name":"Distillation","score":0.6802999973297119},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6172999739646912},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.3815999925136566},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3587000072002411},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.30889999866485596},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.299699991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141000270843506},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558000206947327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.512499988079071},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W10801008","https://openalex.org/W170508173","https://openalex.org/W2963308316","https://openalex.org/W3015752032","https://openalex.org/W3016128928","https://openalex.org/W3024308166","https://openalex.org/W3196313137","https://openalex.org/W4283067311","https://openalex.org/W4385571011","https://openalex.org/W4385822407","https://openalex.org/W4385823321","https://openalex.org/W4402112461","https://openalex.org/W4402116593"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,89],"models":[2,90],"(LLMs)":[3],"have":[4],"demonstrated":[5],"strong":[6],"performance":[7,116],"in":[8,34],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"error":[13],"correction.":[14],"However,":[15],"current":[16],"approaches":[17],"rely":[18],"heavily":[19],"on":[20],"annotated":[21,54],"datasets":[22],"for":[23],"fine-tuning":[24,86],"LLMs,":[25],"which":[26],"are":[27],"often":[28],"costly":[29],"and":[30,79,97,113],"challenging":[31],"to":[32,51,69,110,117],"obtain":[33],"domain-specific":[35],"scenarios.":[36],"To":[37],"address":[38],"this":[39],"limitation,":[40],"we":[41],"propose":[42],"a":[43,57,70,92,98,105,114],"novel":[44],"framework":[45],"that":[46,85],"employs":[47],"Chain-of-Thought":[48],"Distillation":[49],"(CoTD)":[50],"automatically":[52],"generate":[53],"data":[55,96,103],"using":[56],"single-modal":[58],"teacher":[59],"model":[60,73,120],"at":[61],"scale.":[62],"The":[63],"distilled":[64],"knowledge":[65],"is":[66],"subsequently":[67],"transferred":[68],"multimodal":[71,87],"student":[72],"capable":[74],"of":[75,94,101,126],"processing":[76],"both":[77],"audio":[78],"text":[80],"modalities.":[81],"Experimental":[82],"results":[83],"indicate":[84],"large":[88],"with":[91],"combination":[93],"distillation":[95],"limited":[99],"account":[100],"human-annotated":[102,127],"achieves":[104],"relative":[106],"CER":[107],"drop":[108],"compared":[109],"the":[111,118,124],"baseline,":[112],"comparable":[115],"fine-tuned":[119],"utilizing":[121],"five":[122],"times":[123],"amount":[125],"data.":[128]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}