{"id":"https://openalex.org/W4319778963","doi":"https://doi.org/10.1109/iscslp57327.2022.10038107","title":"CorrectSpeech: A Fully Automated System for Speech Correction and Accent Reduction","display_name":"CorrectSpeech: A Fully Automated System for Speech Correction and Accent Reduction","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319778963","doi":"https://doi.org/10.1109/iscslp57327.2022.10038107"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5006527442","display_name":"Daxin Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daxin Tan","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering","Department of Electronic Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046186949","display_name":"Nianzu Zheng","orcid":"https://orcid.org/0000-0001-6300-9684"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Nianzu Zheng","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603207","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0002-9117-8247"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xin Jiang","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011575768","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0001-6501-5922"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Electronic Engineering","Department of Electronic Engineering, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006527442"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4618078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806497812271118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7434718608856201},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6912004351615906},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6713967323303223},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6394603848457336},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.575711727142334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48740842938423157},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4814278781414032},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4807531535625458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4731498956680298},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4575279653072357},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38330578804016113},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.36339378356933594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12562283873558044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09643054008483887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806497812271118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7434718608856201},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6912004351615906},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6713967323303223},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6394603848457336},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.575711727142334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48740842938423157},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4814278781414032},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4807531535625458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4731498956680298},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4575279653072357},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38330578804016113},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36339378356933594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12562283873558044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09643054008483887},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2074231493","https://openalex.org/W2127141656","https://openalex.org/W2737697117","https://openalex.org/W2747874407","https://openalex.org/W2888954148","https://openalex.org/W2955237921","https://openalex.org/W2973142754","https://openalex.org/W2974231335","https://openalex.org/W2998572311","https://openalex.org/W3015430779","https://openalex.org/W3092028330","https://openalex.org/W3096524176","https://openalex.org/W3097777922","https://openalex.org/W3135654121","https://openalex.org/W3160438760","https://openalex.org/W3178546316","https://openalex.org/W3204009030","https://openalex.org/W4221142789","https://openalex.org/W4225596771","https://openalex.org/W4297841480","https://openalex.org/W6767671539","https://openalex.org/W6783867762","https://openalex.org/W6802076607"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2550171623"],"abstract_inverted_index":{"This":[0],"study":[1],"propose":[2],"a":[3,18,114],"fully":[4],"automated":[5],"system":[6,108,127],"for":[7,144],"speech":[8,20,48,86,92,137],"correction":[9,41],"and":[10,49,66,72,82,94,120,133],"accent":[11,135],"reduction.":[12],"Consider":[13],"the":[14,40,46,74,80,89,100],"application":[15],"scenario":[16],"that":[17,29,79,125],"recorded":[19,47],"audio":[21],"contains":[22],"certain":[23],"errors,":[24],"e.g.,":[25],"inappropriate":[26],"words,":[27],"mispronunciations,":[28],"need":[30],"to":[31,63,130],"be":[32],"corrected.":[33],"The":[34,106,122],"proposed":[35,107],"system,":[36],"named":[37],"CorrectSpeech,":[38],"performs":[39],"in":[42,136],"three":[43],"steps:":[44],"recognizing":[45],"converting":[50],"it":[51],"into":[52],"time-stamped":[53],"symbol":[54,58],"sequence,":[55],"aligning":[56],"recognized":[57],"sequence":[59],"with":[60],"target":[61],"text":[62],"determine":[64],"locations":[65],"types":[67],"of":[68,84,91,103,118],"required":[69],"edit":[70],"operations,":[71],"generating":[73],"corrected":[75,85],"speech.":[76],"Experiments":[77],"show":[78],"quality":[81],"naturalness":[83],"depend":[87],"on":[88,111],"performance":[90],"recognition":[93],"alignment":[95],"modules,":[96],"as":[97,99],"well":[98],"granularity":[101],"level":[102],"editing":[104],"operations.":[105],"is":[109,128],"evaluated":[110],"two":[112],"corpora:":[113],"manually":[115],"perturbed":[116],"version":[117],"VCTK":[119],"L2-ARCTIC.":[121],"results":[123],"demonstrate":[124],"our":[126],"able":[129],"correct":[131],"mispronunciation":[132],"reduce":[134],"recordings.":[138],"Audio":[139],"samples":[140],"are":[141],"available":[142],"online":[143],"demonstration":[145],"<sup":[146,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[147,151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[148,152],".":[149],"https://daxintan-cuhk.github.io/CorrectSpeech/":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
