{"id":"https://openalex.org/W4385682917","doi":"https://doi.org/10.1145/3581783.3613753","title":"DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder","display_name":"DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385682917","doi":"https://doi.org/10.1145/3581783.3613753"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","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/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325612","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0001-8606-8273"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013117915","display_name":"Tianyu He","orcid":"https://orcid.org/0000-0002-4828-3228"},"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":"Tianyu He","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522530","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-5631-0639"},"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":"Xu Tan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771326","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"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":"Sheng Zhao","raw_affiliation_strings":["Microsoft Cloud+AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Cloud+AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544241","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-9472-600X"},"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":"Jiang Bian","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035532752"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.3701,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94025264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4281","last_page":"4289"},"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":0.9994000196456909,"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":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9991000294685364,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9854999780654907,"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":0.8227962255477905},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8067653179168701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.671191930770874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6119009256362915},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5669199824333191},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5081698894500732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37463295459747314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33615273237228394},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.19919389486312866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227962255477905},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8067653179168701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671191930770874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6119009256362915},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5669199824333191},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5081698894500732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37463295459747314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33615273237228394},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.19919389486312866},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613753","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2962785568","https://openalex.org/W2972359262","https://openalex.org/W2979894294","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3175528029","https://openalex.org/W3175779516","https://openalex.org/W3211147706","https://openalex.org/W3217030260","https://openalex.org/W4200630629","https://openalex.org/W4226132755","https://openalex.org/W4297793551","https://openalex.org/W4312990833","https://openalex.org/W6602344735"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2752972570","https://openalex.org/W4297051394","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"While":[0],"recent":[1],"research":[2],"has":[3],"made":[4],"significant":[5],"progress":[6],"in":[7,168,211,257],"speech-driven":[8],"talking":[9,76,130],"face":[10,77,131],"generation,":[11],"the":[12,15,30,121,141,154,161,165,171,190,228,237,241,271,274,279],"quality":[13],"of":[14,22,32,192,244,273,282],"generated":[16],"video":[17,132,162,180,225,259],"still":[18],"lags":[19],"behind":[20],"that":[21,90,106,119,187,251],"real":[23],"recordings.":[24],"One":[25],"reason":[26],"for":[27,65,144,213,222,239],"this":[28],"is":[29],"use":[31],"handcrafted":[33],"intermediate":[34],"representations":[35,94,139],"like":[36],"facial":[37,55],"landmarks":[38],"and":[39,49,114,134,158,182,261,277],"3DMM":[40],"coefficients,":[41],"which":[42],"are":[43,50],"designed":[44],"based":[45],"on":[46,75,129,197,233],"human":[47],"knowledge":[48],"insufficient":[51],"to":[52,177,269],"precisely":[53],"describe":[54],"movements.":[56],"Additionally,":[57,216],"these":[58,67,81],"methods":[59,256],"require":[60],"an":[61,72,103,108],"external":[62],"pretrained":[63],"model":[64],"extracting":[66],"representations,":[68],"whose":[69],"performance":[70],"sets":[71],"upper":[73],"bound":[74],"generation.":[78],"To":[79],"address":[80],"limitations,":[82],"we":[83,217],"propose":[84,218],"a":[85,97,111,115,145,198,203,219],"novel":[86,220],"method":[87,221],"called":[88],"DAE-Talker":[89,151,176,252],"leverages":[91],"data-driven":[92],"latent":[93,112,138],"obtained":[95],"from":[96,123,156,170,202],"diffusion":[98],"autoencoder":[99],"(DAE).":[100],"DAE":[101,128,169],"contains":[102],"image":[104,109,117,122,166,230],"encoder":[105],"encodes":[107],"into":[110],"vector":[113],"DDIM-based":[116,229],"decoder":[118,167,231],"reconstructs":[120],"it.":[124],"We":[125,206,264],"train":[126],"our":[127],"frames":[133,163,181,226,246],"then":[135,159],"extract":[136],"their":[137],"as":[140],"training":[142],"target":[143],"Conformer-based":[146],"speech2latent":[147,212],"model.":[148],"During":[149],"inference,":[150],"first":[152],"predicts":[153],"latents":[155],"speech":[157],"generates":[160],"with":[164,189,227],"predicted":[172],"latents.":[173],"This":[174],"allows":[175],"synthesize":[178],"full":[179],"produce":[183],"natural":[184],"head":[185,200],"movements":[186],"align":[188],"content":[191],"speech,":[193],"rather":[194],"than":[195],"relying":[196],"predetermined":[199],"pose":[201,209,214,262,280],"template":[204],"video.":[205],"also":[207,265],"introduce":[208],"modelling":[210,240],"controllability.":[215],"generating":[223],"continuous":[224],"trained":[232],"individual":[234],"frames,":[235],"eliminating":[236],"need":[238],"joint":[242],"distribution":[243],"consecutive":[245],"directly.":[247],"Our":[248],"experiments":[249],"show":[250],"outperforms":[253],"existing":[254],"popular":[255],"lip-sync,":[258],"fidelity,":[260],"naturalness.":[263],"conduct":[266],"ablation":[267],"studies":[268],"analyze":[270],"effectiveness":[272],"proposed":[275],"techniques":[276],"demonstrate":[278],"controllability":[281],"DAE-Talker.":[283]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}