{"id":"https://openalex.org/W4321020784","doi":"https://doi.org/10.1109/fg57933.2023.10042520","title":"Casual chatter or speaking up? Adjusting articulatory effort in generation of speech and animation for conversational characters","display_name":"Casual chatter or speaking up? Adjusting articulatory effort in generation of speech and animation for conversational characters","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4321020784","doi":"https://doi.org/10.1109/fg57933.2023.10042520"},"language":"en","primary_location":{"id":"doi:10.1109/fg57933.2023.10042520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["KTH,Stockholm,Sweden","KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Eva Szekely","raw_affiliation_strings":["KTH,Stockholm,Sweden","KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061415159","display_name":"Simon Alexandersson","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Simon Alexandersson","raw_affiliation_strings":["KTH,Stockholm,Sweden","KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088064508","display_name":"Jonas Beskow","orcid":"https://orcid.org/0000-0003-1399-6604"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonas Beskow","raw_affiliation_strings":["KTH,Stockholm,Sweden","KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015417808"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.1744,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52090797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756468653678894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6728911399841309},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6469238996505737},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.5889542102813721},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5602216124534607},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5514826774597168},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5245054960250854},{"id":"https://openalex.org/keywords/casual","display_name":"Casual","score":0.5041533708572388},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4541182518005371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3503894805908203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2936500906944275},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11802753806114197},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10215774178504944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756468653678894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6728911399841309},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6469238996505737},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.5889542102813721},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5602216124534607},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5514826774597168},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5245054960250854},{"id":"https://openalex.org/C2781426162","wikidata":"https://www.wikidata.org/wiki/Q2275793","display_name":"Casual","level":2,"score":0.5041533708572388},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4541182518005371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3503894805908203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2936500906944275},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11802753806114197},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10215774178504944},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg57933.2023.10042520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1498691477","https://openalex.org/W2139913386","https://openalex.org/W2148985157","https://openalex.org/W2468212864","https://openalex.org/W2550497374","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2747874407","https://openalex.org/W2794490148","https://openalex.org/W2921495256","https://openalex.org/W2937881934","https://openalex.org/W2943399188","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2973177710","https://openalex.org/W3015841875","https://openalex.org/W3029933656","https://openalex.org/W3097483812","https://openalex.org/W3097892637","https://openalex.org/W3111775938","https://openalex.org/W3151309757","https://openalex.org/W3182074706","https://openalex.org/W3193828514","https://openalex.org/W3194605252","https://openalex.org/W3206228555","https://openalex.org/W3207281888","https://openalex.org/W4296069293","https://openalex.org/W4307680525","https://openalex.org/W6750489868","https://openalex.org/W6777705227","https://openalex.org/W6810531757"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W615219140","https://openalex.org/W4232411666","https://openalex.org/W2999276620","https://openalex.org/W1564870812","https://openalex.org/W1978243811","https://openalex.org/W2096968018","https://openalex.org/W2906438086","https://openalex.org/W3040900128"],"abstract_inverted_index":{"Embodied":[0],"conversational":[1,36],"agents":[2],"and":[3,53,55,62,95,109],"social":[4,20],"robots":[5],"need":[6],"to":[7,10,16,105],"be":[8,17,74],"able":[9],"generate":[11,28],"spontaneous":[12,29],"behavior":[13],"in":[14,19],"order":[15],"believable":[18],"interactions.":[21],"We":[22,64],"present":[23],"a":[24,42,66],"system":[25],"that":[26,45],"can":[27,73],"speech":[30,67,77,103],"with":[31],"supporting":[32],"lip":[33],"movements.":[34],"The":[35,76],"TTS":[37,93],"voice":[38],"is":[39,79],"trained":[40],"on":[41],"podcast":[43],"corpus":[44],"has":[46],"been":[47],"prosodically":[48],"tagged":[49],"(f0,":[50],"speaking":[51],"rate":[52],"energy)":[54],"transcribed":[56],"(including":[57],"tokens":[58],"for":[59],"breathing,":[60],"fillers":[61],"laughter).":[63],"introduce":[65],"animation":[68,78],"algorithm":[69],"where":[70],"articulatory":[71],"effort":[72],"adjusted.":[75],"driven":[80],"by":[81],"time-stamped":[82],"phonemes":[83],"obtained":[84],"from":[85,100],"the":[86,92,101,107],"internal":[87],"alignment":[88],"attention":[89],"map":[90],"of":[91],"system,":[94],"we":[96],"use":[97],"prominence":[98],"estimates":[99],"synthesised":[102],"waveform":[104],"modulate":[106],"lip-":[108],"jaw":[110],"movements":[111],"accordingly.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
