{"id":"https://openalex.org/W4224920206","doi":"https://doi.org/10.1109/icassp43922.2022.9746808","title":"Residual-Guided Personalized Speech Synthesis based on Face Image","display_name":"Residual-Guided Personalized Speech Synthesis based on Face Image","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920206","doi":"https://doi.org/10.1109/icassp43922.2022.9746808"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746808","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/A5102003658","display_name":"Jianrong Wang","orcid":"https://orcid.org/0000-0002-8980-1634"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398260","display_name":"Zixuan Wang","orcid":"https://orcid.org/0009-0002-6079-4490"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100944718","display_name":"Xiaosheng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosheng Hu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429597","display_name":"Xuewei Li","orcid":"https://orcid.org/0000-0002-5330-7298"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewei Li","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779069","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-6548-980X"},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]},{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["Chinese Academy of Social Sciences,Institute of Linguistics,Beijing,China","Institute of Linguistics, Chinese Academy of Social Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Social Sciences,Institute of Linguistics,Beijing,China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"raw_affiliation_string":"Institute of Linguistics, Chinese Academy of Social Sciences, Beijing, China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["the Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China","Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4743","last_page":"4747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.822265625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7832046151161194},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6822981834411621},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6406046748161316},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6383380889892578},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.595582127571106},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5567401647567749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.482713907957077},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4653438329696655},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43147727847099304},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06606659293174744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822265625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7832046151161194},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6822981834411621},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6406046748161316},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6383380889892578},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.595582127571106},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5567401647567749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482713907957077},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4653438329696655},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43147727847099304},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06606659293174744},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746808","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1905153633","https://openalex.org/W1965804146","https://openalex.org/W2096733369","https://openalex.org/W2471520273","https://openalex.org/W2752782242","https://openalex.org/W2766049740","https://openalex.org/W2766812927","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2884585870","https://openalex.org/W2888888638","https://openalex.org/W2889326414","https://openalex.org/W2962788625","https://openalex.org/W2963609956","https://openalex.org/W2963839617","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2979157532","https://openalex.org/W3010434693","https://openalex.org/W3040867037","https://openalex.org/W3096806995","https://openalex.org/W4298580827","https://openalex.org/W6736996214","https://openalex.org/W6745697700","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6753412334","https://openalex.org/W6774285787","https://openalex.org/W6780730699"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"Previous":[0],"works":[1],"derive":[2],"personalized":[3,40,48,139],"speech":[4,31,41,49,63,66,82,98,130,140],"features":[5,42],"by":[6,79,132,142],"training":[7,143],"the":[8,30,91,96,101,105,129,138],"model":[9,134],"on":[10],"a":[11,26,62,65,69,84,117,144],"large":[12,145],"dataset":[13],"composed":[14],"of":[15,107,147],"his/her":[16],"audio":[17,148],"sounds.":[18],"It":[19],"was":[20],"reported":[21],"that":[22,128],"face":[23,70,92,123],"information":[24],"has":[25],"strong":[27],"link":[28],"with":[29],"sound.":[32],"Thus":[33],"in":[34,100,150],"this":[35,77],"work,":[36],"we":[37,115],"innovatively":[38],"extract":[39],"from":[43],"human":[44],"faces":[45],"to":[46,89,94,137],"synthesize":[47],"using":[50],"neural":[51],"vocoder.":[52],"A":[53],"Face-based":[54],"Residual":[55],"Personalized":[56],"Speech":[57],"Synthesis":[58],"Model":[59],"(FR-PSS)":[60],"containing":[61],"encoder,":[64],"synthesizer":[67],"and":[68,111],"encoder":[71],"is":[72,87,135],"designed":[73],"for":[74,122],"PSS.":[75],"In":[76],"model,":[78],"designing":[80],"two":[81],"priors,":[83],"residual-guided":[85],"strategy":[86],"introduced":[88],"guide":[90],"feature":[93,99],"approach":[95],"true":[97],"training.":[102],"Moreover,":[103],"considering":[104],"error":[106],"feature\u2019s":[108],"absolute":[109],"values":[110],"their":[112],"directional":[113],"bias,":[114],"formulate":[116],"novel":[118],"tri-item":[119],"loss":[120],"function":[121],"encoder.":[124],"Experimental":[125],"results":[126],"show":[127],"synthesized":[131,141],"our":[133],"comparable":[136],"amount":[146],"data":[149],"previous":[151],"works.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}