{"id":"https://openalex.org/W3194357576","doi":"https://doi.org/10.1109/icassp43922.2022.9747380","title":"Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary","display_name":"Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3194357576","doi":"https://doi.org/10.1109/icassp43922.2022.9747380","mag":"3194357576"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747380","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/A5101704266","display_name":"Sibo Zhang","orcid":"https://orcid.org/0000-0003-1037-3970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sibo Zhang","raw_affiliation_strings":["Baidu Research,USA","Baidu Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,USA","institution_ids":[]},{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["Baidu Research,USA","Baidu Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,USA","institution_ids":[]},{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053378837","display_name":"Miao Liao","orcid":"https://orcid.org/0000-0003-3378-3817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao Liao","raw_affiliation_strings":["Baidu Research,USA","Baidu Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,USA","institution_ids":[]},{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843626","display_name":"Liangjun Zhang","orcid":"https://orcid.org/0000-0001-5737-2540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangjun Zhang","raw_affiliation_strings":["Baidu Research,USA","Baidu Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,USA","institution_ids":[]},{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5889,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93096287,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2659","last_page":"2663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991999864578247,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991999864578247,"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":0.9973999857902527,"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":0.9961000084877014,"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":0.8731141686439514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6135092973709106},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6134805679321289},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5591240525245667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5453330278396606},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4609193801879883},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4297953248023987},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3575090169906616},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3544394075870514},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2235577404499054},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1961991786956787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8731141686439514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6135092973709106},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6134805679321289},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5591240525245667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453330278396606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4609193801879883},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4297953248023987},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3575090169906616},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3544394075870514},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2235577404499054},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1961991786956787},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747380","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1482998036","https://openalex.org/W2000911139","https://openalex.org/W2029996593","https://openalex.org/W2099257899","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2903831537","https://openalex.org/W2942074357","https://openalex.org/W2944294033","https://openalex.org/W2960274051","https://openalex.org/W2962730651","https://openalex.org/W2962795401","https://openalex.org/W2963290645","https://openalex.org/W2963841322","https://openalex.org/W2995238198","https://openalex.org/W3095757630","https://openalex.org/W3097792222","https://openalex.org/W3109875893","https://openalex.org/W3127686677","https://openalex.org/W6650605322","https://openalex.org/W6753914649","https://openalex.org/W6756633688","https://openalex.org/W6771661716","https://openalex.org/W6783567862","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4313289316","https://openalex.org/W4377967120","https://openalex.org/W4288040045","https://openalex.org/W3195938642","https://openalex.org/W4290612991","https://openalex.org/W2410085756","https://openalex.org/W2963958000","https://openalex.org/W4322155169","https://openalex.org/W2903193238","https://openalex.org/W4301772310"],"abstract_inverted_index":{"With":[0],"the":[1,34,77,105,130,151],"advance":[2],"of":[3,67,76,145,155],"deep":[4],"learning":[5],"technology,":[6],"automatic":[7],"video":[8,32,51,59],"generation":[9,60,137],"from":[10,33,52,110],"audio":[11],"or":[12],"text":[13],"has":[14,64],"become":[15],"an":[16],"emerging":[17],"and":[18,42,92,107,143,153],"promising":[19],"research":[20],"topic.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"present":[26],"a":[27,39,44,65,140],"novel":[28],"approach":[29,63],"to":[30,49,57,95,98,116,128],"synthesize":[31],"text.":[35],"The":[36,148],"method":[37,132],"builds":[38],"phoneme-pose":[40],"dictionary":[41],"trains":[43],"generative":[45],"adversarial":[46],"network":[47],"(GAN)":[48],"generate":[50],"interpolated":[53],"phoneme":[54],"poses.":[55],"Compared":[56],"audio-driven":[58,85],"algorithms,":[61],"our":[62,146,156],"number":[66],"advantages:":[68],"1)":[69],"It":[70,88,102],"only":[71],"needs":[72],"about":[73],"1":[74],"min":[75],"training":[78,108],"data,":[79],"which":[80,119],"is":[81,89,120],"significantly":[82,103],"less":[83],"than":[84],"approaches;":[86],"2)":[87],"more":[90],"flexible":[91],"not":[93],"subject":[94],"vulnerability":[96],"due":[97],"speaker":[99],"variation;":[100],"3)":[101],"reduces":[104],"preprocessing":[106],"time":[109],"several":[111],"days":[112],"for":[113],"audio-based":[114],"methods":[115,138],"4":[117],"hours,":[118],"10":[121],"times":[122],"faster.":[123],"We":[124],"perform":[125],"extensive":[126],"experiments":[127],"compare":[129],"proposed":[131],"with":[133],"state-of-the-art":[134],"talking":[135],"face":[136],"on":[139],"benchmark":[141],"dataset":[142],"datasets":[144],"own.":[147],"results":[149],"demonstrate":[150],"effectiveness":[152],"superiority":[154],"approach.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}