{"id":"https://openalex.org/W4372266905","doi":"https://doi.org/10.1109/icassp49357.2023.10096194","title":"UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction","display_name":"UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266905","doi":"https://doi.org/10.1109/icassp49357.2023.10096194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096194","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.05689","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060023404","display_name":"Jiaxin Guo","orcid":"https://orcid.org/0000-0002-2314-8804"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxin Guo","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033151808","display_name":"Minghan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghan Wang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065926428","display_name":"Xiaosong Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosong Qiao","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012613066","display_name":"Daimeng Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daimeng Wei","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032580454","display_name":"Hengchao Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengchao Shang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016271188","display_name":"Zongyao Li","orcid":"https://orcid.org/0000-0002-3300-1806"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongyao Li","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028173644","display_name":"Zhengzhe Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengzhe Yu","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015420720","display_name":"Yinglu Li","orcid":"https://orcid.org/0000-0001-5852-9247"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglu Li","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115781256","display_name":"Chang Su","orcid":"https://orcid.org/0000-0003-3112-2724"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Su","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5060023404"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3516,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63845949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9998999834060669,"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8015186190605164},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6823168396949768},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.6667138338088989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6112409830093384},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5468019247055054},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5411990284919739},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5304163098335266},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5078838467597961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076180696487427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42761099338531494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1936810314655304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16074520349502563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08150124549865723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015186190605164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6823168396949768},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.6667138338088989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6112409830093384},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5468019247055054},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5411990284919739},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5304163098335266},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5078838467597961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076180696487427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42761099338531494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1936810314655304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16074520349502563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08150124549865723},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096194","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.05689","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05689","pdf_url":"https://arxiv.org/pdf/2401.05689","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.05689","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.05689","pdf_url":"https://arxiv.org/pdf/2401.05689","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372266905.pdf","grobid_xml":"https://content.openalex.org/works/W4372266905.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1495461096","https://openalex.org/W2896457183","https://openalex.org/W2946375144","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W3097777922","https://openalex.org/W3111562797","https://openalex.org/W3160523328","https://openalex.org/W3170405627","https://openalex.org/W3203407300","https://openalex.org/W4221167707","https://openalex.org/W4291566970","https://openalex.org/W4385245566","https://openalex.org/W6629743249","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6762471145","https://openalex.org/W6787040858","https://openalex.org/W6794876948","https://openalex.org/W6797037654"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2980068837","https://openalex.org/W2098872742","https://openalex.org/W168676510"],"abstract_inverted_index":{"Error":[0,97],"correction":[1,179],"techniques":[2],"have":[3,53],"been":[4],"used":[5],"to":[6,114,122,129,135],"refine":[7],"the":[8,64,104,117,131,137,142,150,176,203],"output":[9],"sentences":[10],"from":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR)":[15],"models":[16,30,52,180,216],"and":[17,31,39,82,127,146,169,190,210],"achieve":[18],"a":[19,72,78,182,186],"lower":[20],"word":[21],"error":[22,138,156],"rate":[23],"(WER).":[24],"Previous":[25],"works":[26],"usually":[27],"adopt":[28],"end-to-end":[29],"has":[32,100],"strong":[33],"dependency":[34,102],"on":[35,47,56,60,103,141,218],"Pseudo":[36,48],"Paired":[37,41,49,62],"Data":[38],"Original":[40,61],"Data.":[42],"But":[43],"when":[44],"only":[45],"pre-training":[46],"Data,":[50,63],"previous":[51],"negative":[54],"effect":[55],"correction.":[57],"While":[58],"fine-tuning":[59,168],"source":[65],"side":[66],"data":[67,106],"must":[68],"be":[69],"transcribed":[70],"by":[71,181],"well-trained":[73],"ASR":[74,96,155,204,215],"model,":[75],"which":[76],"takes":[77],"lot":[79],"of":[80,152,202,214],"time":[81],"not":[83],"universal.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"propose":[89],"UCorrect,":[90],"an":[91,194],"unsupervised":[92],"Detector-Generator-Selector":[93],"framework":[94],"for":[95,154],"Correction.":[98],"UCorrect":[99,153],"no":[101],"training":[105],"mentioned":[107],"before.":[108],"The":[109],"whole":[110],"procedure":[111],"is":[112,119,193],"first":[113],"detect":[115],"whether":[116],"character":[118],"erroneous,":[120],"then":[121],"generate":[123],"some":[124],"candidate":[125],"characters":[126],"finally":[128],"select":[130],"most":[132],"confident":[133],"one":[134],"replace":[136],"character.":[139],"Experiments":[140],"public":[143],"AISHELL-1":[144],"dataset":[145,148],"WenetSpeech":[147],"show":[149],"effectiveness":[151],"correction:":[157],"1)":[158],"it":[159,174,192,198],"achieves":[160,164],"significant":[161],"WER":[162],"reduction,":[163],"6.83%":[165],"even":[166],"without":[167],"14.29%":[170],"after":[171],"fine-tuning;":[172],"2)":[173],"outperforms":[175],"popular":[177],"NAR":[178],"large":[183],"margin":[184],"with":[185,206],"competitive":[187],"low":[188],"latency;":[189],"3)":[191],"universal":[195],"method,":[196],"as":[197],"reduces":[199,211],"all":[200,212],"WERs":[201,213],"model":[205],"different":[207,219],"decoding":[208],"strategies":[209],"trained":[217],"scale":[220],"datasets.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}