{"id":"https://openalex.org/W2897663715","doi":"https://doi.org/10.1145/3240508.3240601","title":"Face-Voice Matching using Cross-modal Embeddings","display_name":"Face-Voice Matching using Cross-modal Embeddings","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2897663715","doi":"https://doi.org/10.1145/3240508.3240601","mag":"2897663715"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240601","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","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/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Hitachi, Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi, Ltd., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":1.5972,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.91380138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1011","last_page":"1019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.778298020362854},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.763491690158844},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7443221807479858},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6449803709983826},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6202276945114136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5562475323677063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5345301628112793},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4338744282722473},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42564791440963745},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4078902304172516},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3605734705924988},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09417745471000671}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778298020362854},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.763491690158844},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7443221807479858},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6449803709983826},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6202276945114136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562475323677063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5345301628112793},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4338744282722473},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42564791440963745},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4078902304172516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3605734705924988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09417745471000671},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240601","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1971887133","https://openalex.org/W2004909598","https://openalex.org/W2015143272","https://openalex.org/W2019464758","https://openalex.org/W2042311736","https://openalex.org/W2065979868","https://openalex.org/W2066078528","https://openalex.org/W2071522329","https://openalex.org/W2077881910","https://openalex.org/W2096733369","https://openalex.org/W2101036994","https://openalex.org/W2103208299","https://openalex.org/W2107634464","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2114404361","https://openalex.org/W2125336414","https://openalex.org/W2130556178","https://openalex.org/W2136879537","https://openalex.org/W2138621090","https://openalex.org/W2140831887","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2167709189","https://openalex.org/W2186274992","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2227324914","https://openalex.org/W2266401008","https://openalex.org/W2403149086","https://openalex.org/W2474574787","https://openalex.org/W2515770085","https://openalex.org/W2520774990","https://openalex.org/W2555897561","https://openalex.org/W2613997951","https://openalex.org/W2621109248","https://openalex.org/W2726515241","https://openalex.org/W2736262075","https://openalex.org/W2737041163","https://openalex.org/W2737691244","https://openalex.org/W2772736377","https://openalex.org/W2781292787","https://openalex.org/W2963026686","https://openalex.org/W2963887950","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2103413230","https://openalex.org/W2391245565","https://openalex.org/W1899364738","https://openalex.org/W43171467","https://openalex.org/W2248182120","https://openalex.org/W2134472250","https://openalex.org/W2908959303","https://openalex.org/W2347601237","https://openalex.org/W2897995864","https://openalex.org/W1775397219"],"abstract_inverted_index":{"Face-voice":[0],"matching":[1,24,49,95],"is":[2,28],"a":[3,47,63],"task":[4,96],"to":[5,132],"find":[6],"correspondence":[7],"between":[8,55],"faces":[9],"and":[10,37,58,72,87,101,113,119],"voices.":[11],"Many":[12],"researches":[13],"in":[14,21,38,136],"cognitive":[15,137],"science":[16,138],"have":[17],"confirmed":[18],"human":[19,33,133],"ability":[20,27],"the":[22,82,88,106,117,120,123],"face-voice":[23,48],"tasks.":[25],"Such":[26],"useful":[29],"for":[30],"creating":[31],"natural":[32],"machine":[34],"interaction":[35],"systems":[36],"many":[39],"other":[40],"applications.":[41],"In":[42,92],"this":[43],"paper,":[44],"we":[45],"propose":[46],"model":[50,110],"that":[51],"learns":[52],"cross-modal":[53],"embeddings":[54],"face":[56,70,84],"images":[57,71],"voice":[59],"characteristics.":[60],"We":[61],"constructed":[62],"novel":[64],"FVCeleb":[65,118],"dataset":[66,86],"which":[67],"consists":[68],"of":[69,105,122],"utterances":[73],"from":[74,81],"1,078":[75],"persons.":[76],"These":[77,127],"persons":[78],"were":[79],"selected":[80],"MS-Celeb-1M":[83],"image":[85],"VoxCeleb":[89],"audio":[90,99],"dataset.":[91],"two-alternative":[93],"forced-choice":[94],"with":[97],"an":[98],"input":[100],"two":[102],"face-image":[103],"candidates":[104],"same":[107],"gender,":[108],"our":[109],"achieved":[111],"62.2%":[112],"56.5%":[114],"accuracy":[115],"on":[116],"subset":[121],"GRID":[124],"corpus,":[125],"respectively.":[126],"results":[128],"are":[129],"very":[130],"similar":[131],"performance":[134],"reported":[135],"studies.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}