{"id":"https://openalex.org/W4372262415","doi":"https://doi.org/10.1109/icassp49357.2023.10095684","title":"Naturalistic Head Motion Generation from Speech","display_name":"Naturalistic Head Motion Generation from Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262415","doi":"https://doi.org/10.1109/icassp49357.2023.10095684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5086565759","display_name":"Trisha Mittal","orcid":"https://orcid.org/0000-0003-3558-6518"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trisha Mittal","raw_affiliation_strings":["University of Maryland,Department of Computer Science,College Park","Department of Computer Science, University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,Department of Computer Science,College Park","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000858764","display_name":"Masha Fedzechkina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Masha Fedzechkina","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077788104","display_name":"Anurag Ranjan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anurag Ranjan","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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/T12290","display_name":"Human Motion and Animation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.7520409822463989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400045394897461},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7325051426887512},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.692395031452179},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6274254322052002},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5853351950645447},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5698909759521484},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5462297201156616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5125279426574707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103458762168884},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43680596351623535},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.43669548630714417},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.43332940340042114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3295682668685913},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32005396485328674},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11247122287750244},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08700358867645264},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07513919472694397}],"concepts":[{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.7520409822463989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400045394897461},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7325051426887512},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.692395031452179},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6274254322052002},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5853351950645447},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5698909759521484},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5462297201156616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5125279426574707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103458762168884},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43680596351623535},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.43669548630714417},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.43332940340042114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3295682668685913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32005396485328674},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11247122287750244},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08700358867645264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07513919472694397},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2005030514","https://openalex.org/W2054721804","https://openalex.org/W2118004237","https://openalex.org/W2142487393","https://openalex.org/W2403714865","https://openalex.org/W2738406145","https://openalex.org/W2747308422","https://openalex.org/W2769666294","https://openalex.org/W2802076562","https://openalex.org/W2962795401","https://openalex.org/W3035724791","https://openalex.org/W3083173864","https://openalex.org/W3094612121","https://openalex.org/W3125775899","https://openalex.org/W3172598908","https://openalex.org/W3180794345","https://openalex.org/W3211976544","https://openalex.org/W4200174933","https://openalex.org/W4252434905","https://openalex.org/W4312309978","https://openalex.org/W6681380790","https://openalex.org/W6797004501"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Synthesizing":[0],"natural":[1],"head":[2,28,46,66,80,113],"motion":[3,29,47],"to":[4,49,124],"accompany":[5,50],"speech":[6,52],"for":[7,14,121],"an":[8,38,118],"embodied":[9],"conversational":[10],"agent":[11],"is":[12],"necessary":[13],"pro-viding":[15],"a":[16,34,51,70],"rich":[17],"interactive":[18],"experience.":[19],"Most":[20],"prior":[21],"works":[22],"assess":[23],"the":[24,59,62,82,108],"quality":[25,64,110],"of":[26,65,90,111,134],"generated":[27,112],"by":[30],"comparing":[31],"them":[32],"against":[33],"single":[35],"ground-truth":[36],"using":[37],"objective":[39,97,127],"metric.":[40],"Yet":[41],"there":[42],"are":[43],"many":[44],"plausible":[45],"sequences":[48],"utterance.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"study":[58],"variation":[60],"in":[61,101],"perceptual":[63,91,109],"motions":[67,86],"sampled":[68],"from":[69],"generative":[71,83],"model.":[72],"We":[73,93],"show":[74,95],"that,":[75],"despite":[76],"providing":[77],"more":[78],"di-verse":[79],"motions,":[81],"model":[84],"produces":[85],"with":[87,131],"varying":[88],"degrees":[89],"quality.":[92,135],"finally":[94],"that":[96,129],"metrics":[98,128],"commonly":[99],"used":[100],"previous":[102],"research":[103],"do":[104],"not":[105],"accurately":[106],"reflect":[107],"motions.":[114],"These":[115],"results":[116],"open":[117],"interesting":[119],"avenue":[120],"future":[122],"work":[123],"investigate":[125],"better":[126],"correlate":[130],"human":[132],"perception":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}