{"id":"https://openalex.org/W2987026005","doi":"https://doi.org/10.1109/taslp.2019.2950602","title":"Cross-Domain Deep Visual Feature Generation for Mandarin Audio\u2013Visual Speech Recognition","display_name":"Cross-Domain Deep Visual Feature Generation for Mandarin Audio\u2013Visual Speech Recognition","publication_year":2019,"publication_date":"2019-10-31","ids":{"openalex":"https://openalex.org/W2987026005","doi":"https://doi.org/10.1109/taslp.2019.2950602","mag":"2987026005"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2950602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2950602","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences and Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7228-5768","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences and Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6725-1160","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824297","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0003-4304-2342"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101684375","display_name":"Jingzhou Yang","orcid":"https://orcid.org/0000-0002-5092-6739"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingzhou Yang","raw_affiliation_strings":["Microsoft China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5092-6739","affiliations":[{"raw_affiliation_string":"Microsoft China, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1696,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88678556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"185","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143426179885864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8118536472320557},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6519447565078735},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6456360816955566},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6333692669868469},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5346452593803406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47586387395858765},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4289604723453522},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41644224524497986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33460304141044617},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3009169101715088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143426179885864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8118536472320557},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6519447565078735},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6456360816955566},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6333692669868469},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5346452593803406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47586387395858765},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4289604723453522},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41644224524497986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33460304141044617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3009169101715088},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2950602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2950602","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1322429633","display_name":null,"funder_award_id":"2019B090915002","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"},{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3571483920","display_name":null,"funder_award_id":"MMT-p1-19","funder_id":"https://openalex.org/F4320335138","funder_display_name":"Shun Hing Institute of Advanced Engineering"},{"id":"https://openalex.org/G6611988724","display_name":"\u65e9\u671f\u963f\u5c14\u8328\u6d77\u9ed8\u75c7\u7684\u8a00\u8bed\u7279\u5f81\u53d8\u5f02\u6027\u53ca\u5176\u795e\u7ecf\u673a\u5236\u7814\u7a76","funder_award_id":"61771461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7974680614","display_name":null,"funder_award_id":"4055065","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335138","display_name":"Shun Hing Institute of Advanced Engineering","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1454360699","https://openalex.org/W1499332833","https://openalex.org/W1503933356","https://openalex.org/W1524333225","https://openalex.org/W1531956331","https://openalex.org/W1731081199","https://openalex.org/W1875842236","https://openalex.org/W1989588065","https://openalex.org/W1990353734","https://openalex.org/W1999681822","https://openalex.org/W2002352051","https://openalex.org/W2011845089","https://openalex.org/W2013598660","https://openalex.org/W2015394094","https://openalex.org/W2022799064","https://openalex.org/W2027297142","https://openalex.org/W2070726616","https://openalex.org/W2076462394","https://openalex.org/W2104999023","https://openalex.org/W2124460610","https://openalex.org/W2128173845","https://openalex.org/W2128176022","https://openalex.org/W2131342762","https://openalex.org/W2131770202","https://openalex.org/W2136922672","https://openalex.org/W2153682659","https://openalex.org/W2155273149","https://openalex.org/W2159505618","https://openalex.org/W2160815625","https://openalex.org/W2167206253","https://openalex.org/W2183272744","https://openalex.org/W2184549941","https://openalex.org/W2188183693","https://openalex.org/W2296705629","https://openalex.org/W2406846463","https://openalex.org/W2507804770","https://openalex.org/W2512544816","https://openalex.org/W2515372520","https://openalex.org/W2538370046","https://openalex.org/W2551572271","https://openalex.org/W2604496056","https://openalex.org/W2696259631","https://openalex.org/W2790326622","https://openalex.org/W2885130944","https://openalex.org/W2889058932","https://openalex.org/W2890952074","https://openalex.org/W2901907199","https://openalex.org/W2935794029","https://openalex.org/W2952746495","https://openalex.org/W2963597470","https://openalex.org/W2963654155","https://openalex.org/W6631362777","https://openalex.org/W6637618735","https://openalex.org/W6683078286","https://openalex.org/W6685833255","https://openalex.org/W6697336780","https://openalex.org/W6713551954","https://openalex.org/W6725226244","https://openalex.org/W6726406164"],"related_works":["https://openalex.org/W2162582511","https://openalex.org/W107086600","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W2008737763"],"abstract_inverted_index":{"There":[0],"has":[1,100],"been":[2,101],"a":[3,108],"long":[4],"term":[5],"interest":[6],"in":[7,26,64,72],"using":[8,178],"visual":[9,22,29,40,60,136,151,182],"information":[10,23],"to":[11,52,58,96,119,138,196],"improve":[12],"automatic":[13],"speech":[14,30,161,172],"recognition":[15,31,162],"(ASR)":[16],"system":[17],"performance.":[18],"Both":[19],"audio":[20,28],"and":[21,85,168,211],"are":[24],"required":[25],"conventional":[27],"(AVSR)":[32],"systems.":[33],"This":[34],"limits":[35],"their":[36],"wider":[37],"applications":[38],"when":[39],"modality":[41],"is":[42,51],"not":[43,89],"present.":[44],"To":[45],"this":[46,65,106],"end,":[47],"one":[48],"possible":[49],"solution":[50],"use":[53],"acoustic-to-visual":[54],"(A2V)":[55],"inversion":[56,73,126,132],"techniques":[57,154],"generate":[59],"features.":[61],"Previous":[62],"research":[63],"direction":[66],"used":[67,118],"synthetic":[68],"acoustic-articulatory":[69],"parallel":[70,83],"data":[71,84,87,143],"model":[74],"training.":[75],"The":[76,147,174],"acoustic":[77,142],"mismatch":[78],"between":[79],"the":[80,93,131,179,186],"audio-visual":[81],"(AV)":[82],"target":[86,94],"was":[88,117],"considered.":[90],"In":[91,105],"addition,":[92],"language":[95],"apply":[97],"these":[98],"technologies":[99],"focused":[102],"on":[103,157],"English.":[104],"article,":[107],"real":[109],"3D":[110],"Audio-Visual":[111],"Mandarin":[112,160],"Continuous":[113],"Speech":[114],"(3DAV-MCS)":[115],"corpus":[116],"train":[120],"deep":[121,150],"neural":[122,189],"network":[123,190],"based":[124],"A2V":[125],"models.":[127],"Cross-domain":[128],"adaptation":[129],"of":[130,144],"models":[133],"allows":[134],"suitable":[135],"features":[137,183],"be":[139],"generated":[140,181],"from":[141],"mismatched":[145],"domains.":[146],"proposed":[148],"cross-domain":[149,180],"feature":[152],"generation":[153],"were":[155,215],"evaluated":[156],"two":[158],"state-of-the-art":[159],"tasks:":[163],"DAPRA":[164],"GALE":[165],"broadcast":[166],"transcription":[167],"BOLT":[169],"conversational":[170],"telephone":[171],"recognition.":[173],"AVSR":[175],"systems":[176,193],"constructed":[177],"consistently":[184],"outperformed":[185],"baseline":[187],"convolutional":[188],"(CNN)":[191],"ASR":[192],"by":[194],"up":[195],"3.3%":[197],"absolute":[198],"(9.1%":[199],"relative)":[200],"character":[201],"error":[202],"rate":[203],"(CER)":[204],"reductions":[205],"after":[206],"both":[207],"speaker":[208],"adaptive":[209],"training":[210,214],"sequence":[212],"discriminative":[213],"performed.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}