{"id":"https://openalex.org/W2404408055","doi":"https://doi.org/10.21437/interspeech.2014-137","title":"Speaker diarization using eye-gaze information in multi-party conversations","display_name":"Speaker diarization using eye-gaze information in multi-party conversations","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2404408055","doi":"https://doi.org/10.21437/interspeech.2014-137","mag":"2404408055"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5058775745","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0002-2929-2559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koji Inoue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103010851","display_name":"Yukoh Wakabayashi","orcid":"https://orcid.org/0000-0001-8846-3699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukoh Wakabayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023501753","display_name":"Hiromasa Yoshimoto","orcid":"https://orcid.org/0000-0001-9702-2879"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiromasa Yoshimoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"566"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9343037605285645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953262329101562},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7701228857040405},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.6665550470352173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6401069760322571},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5284887552261353},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5238199830055237},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46338948607444763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3879631757736206},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12219423055648804},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1034211814403534}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9343037605285645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953262329101562},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7701228857040405},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.6665550470352173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6401069760322571},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5284887552261353},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5238199830055237},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46338948607444763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3879631757736206},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12219423055648804},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1034211814403534},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.6463","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.6463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ar.media.kyoto-u.ac.jp/EN/bib/intl/INO-INTERSP14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W58692019","https://openalex.org/W76597279","https://openalex.org/W115540051","https://openalex.org/W1985479696","https://openalex.org/W2025905156","https://openalex.org/W2098013184","https://openalex.org/W2113638573","https://openalex.org/W2141398670","https://openalex.org/W2153842971","https://openalex.org/W2159591770","https://openalex.org/W2171757151","https://openalex.org/W2293592193","https://openalex.org/W2401047175"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"novel":[3],"speaker":[4,17,76,103,112],"diarization":[5,18,104],"method":[6,67,99],"by":[7],"using":[8],"eye-gaze":[9,40,52,70,116],"information":[10,41,71,74],"in":[11,58,62,86,91],"multi-party":[12],"conversations.":[13],"In":[14,38],"real":[15,92],"environ-ments,":[16],"or":[19],"speech":[20],"activity":[21],"detection":[22],"of":[23,26,32,102],"each":[24],"participant":[25],"the":[27,97,106],"conversation":[28],"is":[29,42,49],"challenging":[30],"because":[31],"distant":[33],"talking":[34],"and":[35,47,60],"ambient":[36],"noise.":[37],"contrast,":[39],"robust":[43],"against":[44],"acoustic":[45,73,108],"degradation,":[46],"it":[48],"presumed":[50],"that":[51,96],"behavior":[53],"plays":[54],"an":[55],"important":[56],"role":[57],"turn-taking":[59],"thus":[61],"predicting":[63],"utterances.":[64],"The":[65],"proposed":[66,98],"stochastically":[68],"integrates":[69],"with":[72],"for":[75,83],"diarization.":[77],"Specifically,":[78],"three":[79],"models":[80],"are":[81],"investigated":[82],"multi-modal":[84,114],"integration":[85],"this":[87],"paper.":[88],"Experimental":[89],"eval-uations":[90],"poster":[93],"sessions":[94],"demonstrate":[95],"improves":[100],"accuracy":[101],"from":[105],"base-line":[107],"method.":[109],"Index":[110],"Terms:":[111],"diarization,":[113],"interaction,":[115]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}