{"id":"https://openalex.org/W4225268857","doi":"https://doi.org/10.1109/icassp43922.2022.9746763","title":"ASR Error Correction with Dual-Channel Self-Supervised Learning","display_name":"ASR Error Correction with Dual-Channel Self-Supervised Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225268857","doi":"https://doi.org/10.1109/icassp43922.2022.9746763"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746763","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5100403380","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0001-6087-8243"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108647194","display_name":"Mei Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Tu","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339577","display_name":"Song Liu","orcid":"https://orcid.org/0000-0001-7120-894X"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Liu","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077266611","display_name":"Jinyao Yan","orcid":"https://orcid.org/0000-0003-4153-313X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyao Yan","raw_affiliation_strings":["State Key Laboratory of Media Convergence and Communication, Communication University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China","institution_ids":["https://openalex.org/I75689368"]}]}],"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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7282","last_page":"7286"},"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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":0.831307053565979},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6822550296783447},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6519750952720642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6108441352844238},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.554182767868042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5389187335968018},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5320723056793213},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4781114459037781},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46338021755218506},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.449162095785141},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4232552647590637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38423365354537964},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15140604972839355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.831307053565979},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6822550296783447},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6519750952720642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6108441352844238},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.554182767868042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5389187335968018},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5320723056793213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4781114459037781},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46338021755218506},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.449162095785141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4232552647590637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38423365354537964},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15140604972839355},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746763","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"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":23,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2102113734","https://openalex.org/W2250440945","https://openalex.org/W2294498899","https://openalex.org/W2799473636","https://openalex.org/W2888936194","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2916997151","https://openalex.org/W2963212250","https://openalex.org/W2970671861","https://openalex.org/W3015747801","https://openalex.org/W3034797320","https://openalex.org/W3093312917","https://openalex.org/W3095918555","https://openalex.org/W3096758108","https://openalex.org/W3101648800","https://openalex.org/W3196473441","https://openalex.org/W4385245566","https://openalex.org/W6640362995","https://openalex.org/W6675365184","https://openalex.org/W6739901393","https://openalex.org/W6777644438"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"To":[0],"improve":[1],"the":[2,19,54,66,79,95,103,111,116,147],"performance":[3],"of":[4,39,69,128,151],"Automatic":[5],"Speech":[6],"Recognition":[7],"(ASR),":[8],"it":[9],"is":[10,62],"common":[11],"to":[12,22,64,123,131],"deploy":[13],"an":[14,32,57],"error":[15,33,58,67,80,108],"correction":[16,34],"module":[17],"at":[18,110],"post-processing":[20],"stage":[21],"correct":[23],"recognition":[24],"errors.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,73,106],"propose":[30],"1)":[31],"model,":[35,93],"which":[36,114],"takes":[37],"account":[38],"both":[40],"contextual":[41,87],"information":[42,45,88],"and":[43,149],"phonetic":[44,100],"by":[46],"dual-channel;":[47],"2)":[48],"a":[49,90,125,136],"self-supervised":[50,137],"learning":[51,138],"method":[52],"for":[53,78],"model.":[55,153],"Firstly,":[56],"region":[59],"detection":[60],"model":[61,134],"used":[63],"detect":[65],"regions":[68],"ASR":[70],"output.":[71],"Then,":[72],"perform":[74],"dual-channel":[75],"feature":[76],"extraction":[77],"regions,":[81],"where":[82],"one":[83],"channel":[84,97],"extracts":[85],"their":[86,99],"with":[89],"pre-trained":[91],"language":[92],"while":[94],"other":[96],"builds":[98],"information.":[101],"At":[102],"training":[104],"stage,":[105],"construct":[107],"patterns":[109],"phoneme":[112],"level,":[113],"simplifies":[115],"data":[117,130],"annotation":[118],"procedure,":[119],"thus":[120],"allowing":[121],"us":[122],"leverage":[124],"large":[126],"scale":[127],"unlabeled":[129],"train":[132],"our":[133,152],"in":[135],"manner.":[139],"Experimental":[140],"results":[141],"on":[142],"different":[143],"test":[144],"sets":[145],"demonstrate":[146],"effectiveness":[148],"robustness":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}