{"id":"https://openalex.org/W4304099282","doi":"https://doi.org/10.1145/3503161.3551580","title":"Semantic-aware Responsive Listener Head Synthesis","display_name":"Semantic-aware Responsive Listener Head Synthesis","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304099282","doi":"https://doi.org/10.1145/3503161.3551580"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551580","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5101710970","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0003-0865-1484"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101734540","display_name":"Peng Xiao","orcid":"https://orcid.org/0000-0002-8943-5726"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Xiao","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089712493","display_name":"Rongju Zhang","orcid":"https://orcid.org/0000-0003-4340-7487"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongju Zhang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713692","display_name":"Yijun Wang","orcid":"https://orcid.org/0000-0002-3372-8167"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Wang","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052507628","display_name":"Jianxin Lin","orcid":"https://orcid.org/0000-0003-0359-8821"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Lin","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101710970"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.2458,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39905213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7065","last_page":"7069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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/T11448","display_name":"Face recognition and analysis","score":0.9898999929428101,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9887999892234802,"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":0.808687686920166},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6504412293434143},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5793195366859436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5758600831031799},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4953864812850952},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4889892339706421},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.45357760787010193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44855576753616333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4421989321708679},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42177510261535645},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4162577688694},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40502673387527466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39049220085144043},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.21453967690467834},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14376524090766907},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0971314013004303},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0932449996471405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808687686920166},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6504412293434143},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5793195366859436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5758600831031799},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4953864812850952},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4889892339706421},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.45357760787010193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44855576753616333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4421989321708679},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42177510261535645},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4162577688694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40502673387527466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39049220085144043},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.21453967690467834},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14376524090766907},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0971314013004303},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0932449996471405},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551580","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551580","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2132555391","https://openalex.org/W2133665775","https://openalex.org/W2144499799","https://openalex.org/W2161813860","https://openalex.org/W2237250383","https://openalex.org/W2318890592","https://openalex.org/W2962701817","https://openalex.org/W2962795401","https://openalex.org/W3081492798","https://openalex.org/W3093048956","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3204680331","https://openalex.org/W3204971388"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2464405057"],"abstract_inverted_index":{"Audience":[0],"providing":[1],"proper":[2],"reaction":[3],"during":[4],"a":[5,103,130],"conversation":[6],"can":[7],"bring":[8],"positive":[9],"impact":[10],"to":[11,16,34,49,66,89,122,134],"speaker,":[12,27],"which":[13],"is":[14,48,64,81],"significant":[15],"digital":[17],"human":[18],"and":[19,43,57,75,124,146],"social":[20],"agent":[21],"areas.":[22],"Given":[23],"information":[24,115],"sent":[25],"by":[26,54,112],"responsive":[28,52],"listener":[29,37,51],"head":[30],"synthesis":[31],"task":[32],"aims":[33],"generate":[35],"corresponding":[36],"behaviours":[38],"such":[39],"as":[40],"nodding,":[41],"thinking":[42],"smiling.":[44],"A":[45],"common":[46],"method":[47,86],"build":[50],"pattern":[53],"analyzing":[55],"acoustic":[56,74,123],"facial":[58,76,125],"feature":[59,77],"of":[60,95,153],"speaker.":[61],"However,":[62],"it":[63],"hard":[65],"understand":[67],"what":[68],"speaker":[69],"means,":[70],"purely":[71],"based":[72],"on":[73,150],"since":[78],"numerous":[79],"message":[80],"buried":[82],"in":[83,98,117,120],"language.":[84],"Traditional":[85],"may":[87],"lead":[88],"similar":[90],"results":[91],"ignoring":[92],"the":[93,136,142,147],"diversity":[94],"input.":[96],"Therefore,":[97],"this":[99],"paper":[100],"we":[101,128,140],"presents":[102],"new":[104],"Semantic-aware":[105],"Responsive":[106],"Listener":[107],"Head":[108],"Synthesis":[109],"(SaRLHS)":[110],"approach":[111],"considering":[113],"semantic":[114],"lied":[116],"language":[118],"patterns":[119],"addition":[121],"feature.":[126],"Besides,":[127],"implement":[129],"post-face":[131],"enhancement":[132],"process":[133],"increase":[135],"visual":[137],"effects.":[138],"Moreover,":[139],"won":[141],"People's":[143],"Selection":[144],"Awards":[145],"second":[148],"place":[149],"Grand":[151],"Challenges":[152],"ACM":[154],"2022":[155],"conference.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}