{"id":"https://openalex.org/W4408353790","doi":"https://doi.org/10.1109/icassp49660.2025.10890161","title":"Full-text Error Correction for Chinese Speech Recognition with Large Language Model","display_name":"Full-text Error Correction for Chinese Speech Recognition with Large Language Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353790","doi":"https://doi.org/10.1109/icassp49660.2025.10890161"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890161","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":"conference-paper","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/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111106785","display_name":"Dong Wang","orcid":"https://orcid.org/0009-0009-5836-6260"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, BNRist,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108615106","display_name":"Shen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Huang","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078353046","display_name":"Shidong Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shidong Shang","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9839000105857849,"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":0.9839000105857849,"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":0.8275356292724609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7509950995445251},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6717191934585571},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6349527835845947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5633007884025574},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.46585613489151},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4244476556777954},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.4177432358264923},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10410892963409424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275356292724609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7509950995445251},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6717191934585571},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6349527835845947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5633007884025574},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.46585613489151},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4244476556777954},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.4177432358264923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10410892963409424},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890161","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W2160451571","https://openalex.org/W2916997151","https://openalex.org/W2963308316","https://openalex.org/W3011339933","https://openalex.org/W3016128928","https://openalex.org/W3202576380","https://openalex.org/W4226316089","https://openalex.org/W4283067311","https://openalex.org/W4283745191","https://openalex.org/W4319862712","https://openalex.org/W4385822949","https://openalex.org/W4391021820","https://openalex.org/W4402112066","https://openalex.org/W4402667093","https://openalex.org/W6770528390","https://openalex.org/W6796581206","https://openalex.org/W6857131320","https://openalex.org/W6858893317","https://openalex.org/W6869164663"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2377071794","https://openalex.org/W2252095989","https://openalex.org/W2106335228","https://openalex.org/W2105076537","https://openalex.org/W2380243770","https://openalex.org/W2377495875","https://openalex.org/W2390973415","https://openalex.org/W2074837817","https://openalex.org/W4386590374"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"substantial":[6],"potential":[7],"for":[8,34,45,73,215],"error":[9,46,75,112,153],"correction":[10,47,125],"in":[11,48,196],"Automatic":[12],"Speech":[13],"Recognition":[14],"(ASR).":[15],"However,":[16],"most":[17],"research":[18],"focuses":[19],"on":[20,134,151,160,222],"utterances":[21],"from":[22,54,61],"short-duration":[23],"speech":[24,32,56],"recordings,":[25,57],"which":[26],"are":[27],"the":[28,41,124,135,191,197,223],"predominant":[29],"form":[30],"of":[31,43,111,142],"data":[33],"supervised":[35],"ASR":[36,52],"training.":[37],"This":[38,91,210],"paper":[39],"investigates":[40],"effectiveness":[42],"LLMs":[44,193],"full-text":[49,74,102,152,161,198],"generated":[50],"by":[51],"systems":[53],"longer":[55],"such":[58,114,168],"as":[59,115,169],"transcripts":[60],"podcasts,":[62],"news":[63],"broadcasts,":[64],"and":[65,87,103,105,118,144,147,162,173,184,208],"meetings.":[66],"First,":[67],"we":[68,129,156,188],"develop":[69],"a":[70,80,108,131,139,212],"Chinese":[71],"dataset":[72,92,137,219],"correction,":[76],"named":[77],"ChFT,":[78],"utilizing":[79],"pipeline":[81],"that":[82,190],"involves":[83],"text-to-speech":[84],"synthesis,":[85],"ASR,":[86],"error-correction":[88,175],"pair":[89],"extractor.":[90],"enables":[93],"us":[94],"to":[95,106],"correct":[96],"errors":[97],"across":[98],"contexts,":[99],"including":[100,181],"both":[101],"segment,":[104,163],"address":[107],"broader":[109],"range":[110],"types,":[113],"punctuation":[116],"restoration":[117],"inverse":[119],"text":[120,172],"normalization,":[121],"thus":[122],"making":[123],"process":[126],"comprehensive.":[127],"Second,":[128],"fine-tune":[130],"pre-trained":[132],"LLM":[133],"constructed":[136],"using":[138],"diverse":[140],"set":[141],"prompts":[143,158],"target":[145],"formats,":[146,167],"evaluate":[148],"its":[149,205],"performance":[150],"correction.":[154],"Specifically,":[155],"design":[157],"based":[159],"considering":[164],"various":[165,178],"output":[166],"directly":[170],"corrected":[171],"JSON-based":[174],"pairs.":[176],"Through":[177],"test":[179,186],"settings,":[180],"homogeneous,":[182],"up-to-date,":[183],"hard":[185],"sets,":[187],"find":[189],"finetuned":[192],"perform":[194],"well":[195],"setting":[199],"with":[200],"different":[201],"prompts,":[202],"each":[203],"presenting":[204],"own":[206],"strengths":[207],"weaknesses.":[209],"establishes":[211],"promising":[213],"baseline":[214],"further":[216],"research.":[217],"The":[218],"is":[220],"available":[221],"website<sup":[224],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}