{"id":"https://openalex.org/W7171538085","doi":"https://doi.org/10.48550/arxiv.2607.24430","title":"Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis","display_name":"Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis","publication_year":2026,"publication_date":"2026-07-27","ids":{"openalex":"https://openalex.org/W7171538085","doi":"https://doi.org/10.48550/arxiv.2607.24430"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.24430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.24430","pdf_url":"https://arxiv.org/pdf/2607.24430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.24430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122381512","display_name":"Yifan Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Yifan","raw_affiliation_strings":["Inner Mongolia University Hohhot , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University Hohhot , China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122280225","display_name":"Shuwei He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Shuwei","raw_affiliation_strings":["Inner Mongolia University Hohhot , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University Hohhot , China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137132732","display_name":"Rui Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Rui","raw_affiliation_strings":["Inner Mongolia University Hohhot , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University Hohhot , China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401","observed_orcids":["https://orcid.org/0000-0001-9158-9401"]},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]},{"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, Haizhou","raw_affiliation_strings":["Inner Mongolia University Hohhot , China","SRIBD , School of Artificial Intelligence The Chinese University of Hong Kong Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University Hohhot , China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"SRIBD , School of Artificial Intelligence The Chinese University of Hong Kong Shenzhen , China","institution_ids":["https://openalex.org/I4210116924"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.760699987411499,"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":0.760699987411499,"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/T12031","display_name":"Speech and dialogue systems","score":0.1542000025510788,"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":0.042100001126527786,"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/conversational-speech-synthesis","display_name":"conversational speech synthesis","score":0.9810000061988831},{"id":"https://openalex.org/keywords/facial-expression-modeling","display_name":"facial expression modeling","score":0.9810000061988831},{"id":"https://openalex.org/keywords/multimodal-dialogue","display_name":"multimodal dialogue","score":0.503000020980835},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6919999718666077},{"id":"https://openalex.org/keywords/visual-tokenization","display_name":"visual tokenization","score":0.7609999775886536},{"id":"https://openalex.org/keywords/facial-action-units","display_name":"facial action units","score":0.8309999704360962},{"id":"https://openalex.org/keywords/direct-preference-optimization","display_name":"direct preference optimization","score":0.8220000267028809},{"id":"https://openalex.org/keywords/preference-constraints","display_name":"preference constraints","score":0.35100001096725464},{"id":"https://openalex.org/keywords/facial-expression-perception","display_name":"facial expression perception","score":0.4000000059604645},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127000093460083},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.460999995470047},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4341999888420105},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.37860000133514404},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.3271999955177307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.24430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.24430","pdf_url":"https://arxiv.org/pdf/2607.24430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.24430","doi":"https://doi.org/10.48550/arxiv.2607.24430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.24430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.24430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.24430","pdf_url":"https://arxiv.org/pdf/2607.24430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.557781457901001,"display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1043313185","display_name":null,"funder_award_id":"JCYJ20220818103001002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2567805129","display_name":null,"funder_award_id":"2024QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6473147096","display_name":null,"funder_award_id":"2025JQ011","funder_id":"https://openalex.org/F4320322868","funder_display_name":"Natural Science Foundation of Inner Mongolia"},{"id":"https://openalex.org/G6843083556","display_name":null,"funder_award_id":"62476146","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322868","display_name":"Natural Science Foundation of Inner Mongolia","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7171538085.pdf","grobid_xml":"https://content.openalex.org/works/W7171538085.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415536841","https://openalex.org/W7169797390","https://openalex.org/W7211925559","https://openalex.org/W4416036016","https://openalex.org/W2144514997","https://openalex.org/W4405138899","https://openalex.org/W7151112155","https://openalex.org/W3186700381","https://openalex.org/W1981249440","https://openalex.org/W4402671204"],"abstract_inverted_index":{"Conversational":[0],"Speech":[1],"Synthesis":[2],"is":[3,218],"a":[4,75,81,94,105,120,162,169],"fundamental":[5],"component":[6],"of":[7,47,62,113,148,181,191,235],"human-computer":[8],"interaction,":[9,34],"aiming":[10],"to":[11,143],"generate":[12],"contextually":[13],"appropriate,":[14],"expressive,":[15,221],"and":[16,24,55,139,151,185,198,211,222,239],"empathetic":[17,32],"speech.":[18],"However,":[19],"facial":[20,89,102,114,149],"expressions":[21,150],"encode":[22,88],"subtle":[23],"rich":[25],"affective":[26],"cues":[27],"that":[28,98,202,217],"are":[29],"crucial":[30],"for":[31],"speech":[33,54,140,152,212,216],"whereas":[35],"existing":[36],"approaches":[37],"often":[38],"overlook":[39],"this":[40],"important":[41],"modality.":[42],"In":[43],"addition,":[44],"the":[45,60,129,145,226,233],"lack":[46],"large-scale":[48,163],"natural":[49],"conversational":[50,67,156,227],"datasets":[51],"with":[52,109,187,225],"both":[53,137],"visual":[56,63,96,138],"modalities":[57],"also":[58,231],"limits":[59],"development":[61],"affect":[64],"understanding":[65,147],"in":[66,154,208],"settings.To":[68],"address":[69],"these":[70],"limitations,":[71],"we":[72,91,159],"propose":[73,92],"FacialTalker,":[74],"facial-expression-aware":[76],"CSS":[77],"framework":[78],"built":[79],"upon":[80],"large":[82],"language":[83],"model":[84],"backbone.":[85],"To":[86],"efficiently":[87],"expressions,":[90],"AUTokenizer,":[93],"single-codebook":[95],"tokenizer":[97],"discretizes":[99],"each":[100],"frame-level":[101],"expression":[103],"into":[104],"compact":[106],"token,":[107],"trained":[108],"supervision":[110],"from":[111,173],"combinations":[112],"Action":[115],"Units.":[116],"We":[117],"further":[118],"introduce":[119],"dual":[121],"direct":[122],"preference":[123,134],"optimization":[124],"(DualDPO)":[125],"strategy,":[126],"which":[127],"extends":[128],"DPO":[130],"by":[131],"jointly":[132],"imposing":[133],"constraints":[135],"on":[136],"token":[141],"sequences,":[142],"enhance":[144],"model's":[146],"semantics":[153],"multimodal":[155,164],"contexts.":[157],"Moreover,":[158],"construct":[160],"VSDD-1K,":[161],"dialogue":[165],"dataset":[166,240],"collected":[167],"through":[168],"fully":[170],"automated":[171],"pipeline":[172],"real-world":[174],"Internet":[175],"conversations,":[176],"comprising":[177],"over":[178],"1,033":[179],"hours":[180],"synchronized":[182],"speaker":[183],"videos":[184],"speech,":[186],"more":[188,219],"than":[189],"85\\%":[190],"frames":[192],"containing":[193],"valid":[194],"faces.":[195],"Extensive":[196],"objective":[197],"subjective":[199],"experiments":[200],"demonstrate":[201],"FacialTalker":[203],"consistently":[204],"outperforms":[205],"strong":[206],"baselines":[207],"facial-expression":[209],"perception":[210],"synthesis":[213],"quality,":[214],"generating":[215],"natural,":[220],"better":[223],"aligned":[224],"context.":[228],"The":[229],"results":[230],"validate":[232],"effectiveness":[234],"our":[236],"training":[237],"strategy":[238],"construction":[241],"pipeline.":[242]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-29T00:00:00"}