{"id":"https://openalex.org/W3022855884","doi":"https://doi.org/10.1109/lifetech48969.2020.1570610662","title":"Speaker Identification Method Using Facial Image and Voice","display_name":"Speaker Identification Method Using Facial Image and Voice","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3022855884","doi":"https://doi.org/10.1109/lifetech48969.2020.1570610662","mag":"3022855884"},"language":"en","primary_location":{"id":"doi:10.1109/lifetech48969.2020.1570610662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lifetech48969.2020.1570610662","pdf_url":null,"source":{"id":"https://openalex.org/S4306498653","display_name":"2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech)","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/A5018000109","display_name":"Etsuro Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I203765153","display_name":"Akita University","ror":"https://ror.org/03hv1ad10","country_code":"JP","type":"education","lineage":["https://openalex.org/I203765153"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Etsuro Nakamura","raw_affiliation_strings":["Graduate School of Engineering Science, Akita University, Akita, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Akita University, Akita, Japan","institution_ids":["https://openalex.org/I203765153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030252329","display_name":"Yoichi Kageyama","orcid":"https://orcid.org/0000-0001-9958-1228"},"institutions":[{"id":"https://openalex.org/I203765153","display_name":"Akita University","ror":"https://ror.org/03hv1ad10","country_code":"JP","type":"education","lineage":["https://openalex.org/I203765153"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Kageyama","raw_affiliation_strings":["Graduate School of Engineering Science, Akita University, Akita, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Akita University, Akita, Japan","institution_ids":["https://openalex.org/I203765153"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058735706","display_name":"Motonari Shirasu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motonari Shirasu","raw_affiliation_strings":["Business Solutions Division, Japan Business Systems, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Business Solutions Division, Japan Business Systems, Inc., Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3357,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48717949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9934999942779541,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9861000180244446,"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/computer-science","display_name":"Computer science","score":0.8325669765472412},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7195549011230469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6702397465705872},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6668691039085388},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.625403642654419},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.625213086605072},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6071817278862},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5597373247146606},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.546215295791626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321226716041565},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.496223509311676},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.410073459148407},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10017728805541992},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06272855401039124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325669765472412},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7195549011230469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6702397465705872},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6668691039085388},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.625403642654419},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.625213086605072},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6071817278862},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5597373247146606},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.546215295791626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321226716041565},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.496223509311676},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.410073459148407},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10017728805541992},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06272855401039124},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lifetech48969.2020.1570610662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lifetech48969.2020.1570610662","pdf_url":null,"source":{"id":"https://openalex.org/S4306498653","display_name":"2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2076462394","https://openalex.org/W2284800790","https://openalex.org/W2793493229"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,13,20,33,43,54,62,107,127],"creating":[3],"meeting":[4],"minutes":[5,38],"can":[6,25],"be":[7,27],"substantially":[8],"simplified":[9],"with":[10],"the":[11,18,31,77,105,128],"use":[12],"an":[14,91],"automatic":[15],"system,":[16],"and":[17,23,59,94,113],"efficiency":[19],"subsequent":[21],"meetings":[22],"operations":[24],"also":[26],"improved.":[28],"In":[29,79,109,121],"particular,":[30],"function":[32],"automatically":[34],"assigning":[35,55],"speakers":[36,56,89,129],"to":[37,57,74],"is":[39,72],"crucial.":[40],"Two":[41],"methods":[42],"speaker":[44,119,122],"identification":[45],"have":[46],"been":[47],"widely":[48],"utilized":[49],"in":[50,65,68],"practice;":[51],"a":[52,60,84,95],"method":[53,61,85,98],"cameras,":[58],"registering":[63],"speech":[64],"advance.":[66],"However,":[67],"each":[69],"case,":[70],"it":[71],"necessary":[73],"optimally":[75],"arrange":[76],"equipment.":[78],"this":[80,110],"paper,":[81],"we":[82],"propose":[83],"for":[86,118],"discriminating":[87],"between":[88],"using":[90],"omnidirectional":[92],"camera":[93],"microphone.":[96],"This":[97],"does":[99],"not":[100],"require":[101],"multiple":[102],"devices":[103],"or":[104],"pre-registration":[106],"audio.":[108],"process,":[111],"image":[112],"voice":[114],"data":[115],"are":[116],"used":[117],"identification.":[120],"discrimination":[123],"experiments,":[124],"83.8":[125],"%":[126],"were":[130],"successfully":[131],"discriminated.":[132]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}