{"id":"https://openalex.org/W4416800009","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249172","title":"VICNet: FaderNet-Based Voice Impression Conversion with Affective Dimensional Representation","display_name":"VICNet: FaderNet-Based Voice Impression Conversion with Affective Dimensional Representation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800009","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249172"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5005264920","display_name":"Takuya Takahashi","orcid":"https://orcid.org/0000-0001-6523-0622"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Takahashi","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120437571","display_name":"Saki Kugimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Saki Kugimoto","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34017072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5304999947547913,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5304999947547913,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.12790000438690186,"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/T11448","display_name":"Face recognition and analysis","score":0.07890000194311142,"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/impression","display_name":"Impression","score":0.9563000202178955},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8043000102043152},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5769000053405762},{"id":"https://openalex.org/keywords/impression-formation","display_name":"Impression formation","score":0.47350001335144043},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46639999747276306}],"concepts":[{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.9563000202178955},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8043000102043152},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5769000053405762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5644999742507935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C17822864","wikidata":"https://www.wikidata.org/wiki/Q6007588","display_name":"Impression formation","level":4,"score":0.47350001335144043},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C110346835","wikidata":"https://www.wikidata.org/wiki/Q665141","display_name":"Precedent","level":3,"score":0.4440999925136566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3955000042915344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C4994750","wikidata":"https://www.wikidata.org/wiki/Q1210504","display_name":"Impression management","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2023736093","https://openalex.org/W2091312849","https://openalex.org/W2104074072","https://openalex.org/W2124402513","https://openalex.org/W2126164224","https://openalex.org/W2167557160","https://openalex.org/W2177226811","https://openalex.org/W2404863510","https://openalex.org/W2471520273","https://openalex.org/W2625545704","https://openalex.org/W2726515241","https://openalex.org/W2767461737","https://openalex.org/W3032325810","https://openalex.org/W3162414783","https://openalex.org/W4385822379","https://openalex.org/W4392904630","https://openalex.org/W4393147046"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,43,50,57,82],"voice":[4,10,27,47,66,84,95],"impression":[5,67,73,85,121,128,139],"conversion":[6,68,129],"method":[7,44],"based":[8],"on":[9],"impressions":[11,28,48,96],"quantified":[12],"using":[13,49],"the":[14,71,94,101,116],"valence-arousal-dominance":[15],"(VAD)":[16],"model":[17,118],"commonly":[18],"employed":[19],"for":[20,36,137],"emotional":[21],"expression.":[22],"Conventional":[23],"techniques":[24],"have":[25],"limited":[26,136],"to":[29],"discrete":[30],"categorical":[31],"representations,":[32],"which":[33,64],"presents":[34],"challenges":[35],"versatility.":[37],"In":[38,80],"this":[39],"study,":[40],"we":[41,124],"propose":[42],"of":[45,78,97],"quantifying":[46],"continuous":[51,72],"three-dimensional":[52],"space":[53],"(VAD":[54],"model)":[55],"as":[56],"more":[58],"versatile":[59],"representation,":[60],"and":[61,75],"formulate":[62],"VICNet,":[63],"enables":[65],"by":[69],"incorporating":[70],"representation":[74],"individual":[76],"differences":[77],"listeners.":[79],"addition,":[81],"new":[83],"dataset":[86,103],"was":[87,135],"constructed,":[88],"where":[89],"100":[90,98],"human":[91],"annotators":[92],"assessed":[93],"speakers":[99],"from":[100],"JVS":[102],"in":[104,115],"VAD":[105,113],"space.":[106],"Experimental":[107],"evaluation":[108],"demonstrated":[109],"that":[110,127],"utilising":[111],"all":[112],"axes":[114],"proposed":[117],"enabled":[119],"clearer":[120],"conversion;":[122],"however,":[123],"also":[125],"observed":[126],"performance":[130],"degraded":[131],"when":[132],"training":[133],"data":[134],"certain":[138],"patterns.":[140]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}