{"id":"https://openalex.org/W4321020671","doi":"https://doi.org/10.1109/fg57933.2023.10042714","title":"The Role of Vocal Persona in Natural and Synthesized Speech","display_name":"The Role of Vocal Persona in Natural and Synthesized Speech","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4321020671","doi":"https://doi.org/10.1109/fg57933.2023.10042714"},"language":"en","primary_location":{"id":"doi:10.1109/fg57933.2023.10042714","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg57933.2023.10042714","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/A5015730232","display_name":"Camille Noufi","orcid":"https://orcid.org/0000-0001-8292-0940"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Camille Noufi","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069235453","display_name":"Lloyd May","orcid":"https://orcid.org/0000-0003-4692-8261"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lloyd May","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014707016","display_name":"Jonathan Berger","orcid":"https://orcid.org/0000-0002-9085-0900"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Berger","raw_affiliation_strings":["Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Center for Computer Research in Music and Acoustics, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015730232"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62175218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"327","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9947999715805054,"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"}},{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9939000010490417,"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/persona","display_name":"Persona","score":0.9281120300292969},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6682659387588501},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5775604844093323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5437553524971008},{"id":"https://openalex.org/keywords/augmentative","display_name":"Augmentative","score":0.4803977310657501},{"id":"https://openalex.org/keywords/inclusion","display_name":"Inclusion (mineral)","score":0.47842270135879517},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4325394630432129},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.41454190015792847},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4102388918399811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3807391822338104},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3675054609775543},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29649531841278076},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27943065762519836},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10358333587646484}],"concepts":[{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.9281120300292969},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6682659387588501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5775604844093323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5437553524971008},{"id":"https://openalex.org/C2776465043","wikidata":"https://www.wikidata.org/wiki/Q1358239","display_name":"Augmentative","level":2,"score":0.4803977310657501},{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.47842270135879517},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4325394630432129},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.41454190015792847},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4102388918399811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3807391822338104},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3675054609775543},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29649531841278076},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27943065762519836},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10358333587646484},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg57933.2023.10042714","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/fg57933.2023.10042714","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":0.7400000095367432,"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":29,"referenced_works":["https://openalex.org/W1553689010","https://openalex.org/W1583636673","https://openalex.org/W1600722501","https://openalex.org/W1969601749","https://openalex.org/W1989245305","https://openalex.org/W1995910550","https://openalex.org/W2084969212","https://openalex.org/W2088432713","https://openalex.org/W2129142580","https://openalex.org/W2333217693","https://openalex.org/W2404343848","https://openalex.org/W2502225736","https://openalex.org/W2732142634","https://openalex.org/W2747329762","https://openalex.org/W2750380119","https://openalex.org/W2903140367","https://openalex.org/W2990986341","https://openalex.org/W3015645837","https://openalex.org/W3025528898","https://openalex.org/W3126404598","https://openalex.org/W3132565327","https://openalex.org/W3159066689","https://openalex.org/W3160438760","https://openalex.org/W3198712562","https://openalex.org/W3202871751","https://openalex.org/W4232977219","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6780901240"],"related_works":["https://openalex.org/W2795366572","https://openalex.org/W2886588594","https://openalex.org/W3005214328","https://openalex.org/W2920961600","https://openalex.org/W3091061106","https://openalex.org/W4312802148","https://openalex.org/W2610743940","https://openalex.org/W4285553851","https://openalex.org/W4285550479","https://openalex.org/W1513171822"],"abstract_inverted_index":{"The":[0,119],"inclusion":[1],"of":[2,15,29,50,64,84,92,96,110,129],"voice":[3,7,45],"persona":[4,53,113],"in":[5,11],"synthesized":[6,44],"can":[8],"be":[9],"significant":[10],"a":[12,34,43,55,69,73,93,115],"broad":[13],"range":[14],"human-computer-interaction":[16],"(HCI)":[17],"applications,":[18],"including":[19],"augmentative":[20],"and":[21,27,39,102],"assistive":[22],"communication":[23,117],"(AAC),":[24],"artistic":[25],"performance,":[26],"design":[28,128],"virtual":[30],"agents.":[31],"We":[32,87],"propose":[33],"framework":[35],"to":[36,105,125],"imbue":[37],"compelling":[38],"contextually-dependent":[40,75],"expression":[41],"within":[42,54,72,114],"by":[46,81],"introducing":[47],"the":[48,51,61,82,85,108,111,127,130],"role":[49,109],"vocal":[52,100,112],"synthesis":[56],"system.":[57],"In":[58],"this":[59],"framework,":[60],"resultant":[62],"\u2018tone":[63],"voice\u2019":[65],"is":[66,79],"defined":[67],"as":[68],"point":[70],"existing":[71],"continuous,":[74],"probability":[76],"space":[77],"that":[78],"traversable":[80],"user":[83],"voice.":[86],"also":[88],"present":[89],"initial":[90],"findings":[91],"thematic":[94],"analysis":[95],"10":[97],"interviews":[98],"with":[99],"studies":[101],"performance":[103],"experts":[104],"further":[106],"understand":[107],"natural":[116],"ecology.":[118],"themes":[120],"identified":[121],"are":[122],"then":[123],"used":[124],"inform":[126],"aforementioned":[131],"framework.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
