{"id":"https://openalex.org/W7166813625","doi":"https://doi.org/10.48550/arxiv.2606.31088","title":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","display_name":"Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166813625","doi":"https://doi.org/10.48550/arxiv.2606.31088"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.31088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.31088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109787503","display_name":"Baiqin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Baiqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139763992","display_name":"Sen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Sen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843088","display_name":"Jiankuo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jiankuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735878","display_name":"Xiangyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139762641","display_name":"Zhen Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139825967","display_name":"Xiangyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4754999876022339,"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":0.4754999876022339,"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":0.4702000021934509,"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":0.008799999952316284,"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/conversation","display_name":"Conversation","score":0.6590999960899353},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.6510999798774719},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5879999995231628},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4977000057697296},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.489300012588501},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43650001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294000029563904},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.6510999798774719},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6262000203132629},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4977000057697296},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.31088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.31088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.31088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conversational":[0],"talking":[1,13,99],"face":[2,100],"generation":[3,59,145],"has":[4],"recently":[5],"attracted":[6],"increasing":[7],"attention,":[8],"aiming":[9],"to":[10,22],"synthesize":[11],"interactive":[12,97],"videos":[14],"where":[15],"characters":[16],"speak,":[17],"listen,":[18],"and":[19,47,54,60,91,141,170,182],"respond":[20],"dynamically":[21],"each":[23,124],"other.":[24],"This":[25],"task":[26],"presents":[27],"three":[28,80],"core":[29],"challenges:":[30],"1)":[31],"Flexibility:":[32],"enabling":[33,159],"multi-round":[34,120],"dialogues":[35],"with":[36,185],"an":[37,143],"arbitrary":[38],"number":[39],"of":[40],"participants;":[41],"2)":[42],"Naturalness:":[43],"maintaining":[44,200],"coherent":[45],"motion":[46,136,154],"appropriate":[48],"non-verbal":[49],"feedback":[50,137],"throughout":[51],"the":[52],"interaction;":[53],"3)":[55],"Efficiency:":[56],"achieving":[57],"real-time":[58,109,201],"low":[61],"computation":[62],"overhead":[63],"for":[64,95,147,162],"long-term":[65],"continuous":[66],"online":[67],"conversation.":[68],"Despite":[69],"recent":[70],"advances,":[71],"existing":[72],"methods":[73],"still":[74],"fall":[75],"short":[76],"in":[77],"balancing":[78],"all":[79],"requirements.":[81],"To":[82,131],"bridge":[83],"this":[84],"gap,":[85],"we":[86,134,152,175],"introduce":[87,142],"InterTalk,":[88],"a":[89,104,177],"novel":[90],"efficient":[92],"framework":[93],"designed":[94],"highly":[96],"conversational":[98,121,180],"generation.":[101],"Built":[102],"upon":[103],"motion-based":[105],"architecture,":[106],"InterTalk":[107,194],"supports":[108],"conversation":[110],"synthesis.":[111],"Our":[112],"method":[113],"achieves":[114,195],"strong":[115],"flexibility":[116],"by":[117],"explicitly":[118],"modeling":[119],"dynamics":[122],"among":[123],"participant,":[125],"eliminating":[126],"constraints":[127],"on":[128],"their":[129],"numbers.":[130],"enhance":[132],"interactivity,":[133],"incorporate":[135],"from":[138],"multiple":[139],"participants":[140],"iterative":[144],"strategy":[146],"more":[148],"natural":[149,163],"behaviors.":[150],"Besides,":[151],"disentangle":[153],"into":[155],"several":[156],"facial":[157],"components,":[158],"targeted":[160],"refinements":[161],"response":[164],"such":[165],"as":[166],"precise":[167],"lip":[168],"sync":[169],"realistic":[171],"eye":[172],"blinking.":[173],"Finally,":[174],"construct":[176],"new":[178],"multi-person":[179],"dataset":[181],"enrich":[183],"it":[184],"3D":[186],"face-based":[187],"data":[188],"augmentation.":[189],"Extensive":[190],"experiments":[191],"demonstrate":[192],"that":[193],"superior":[196],"interaction":[197],"quality":[198],"while":[199],"performance":[202],"at":[203],"30":[204],"FPS.":[205]},"counts_by_year":[],"updated_date":"2026-07-02T06:18:51.028212","created_date":"2026-07-02T00:00:00"}