{"id":"https://openalex.org/W2402441703","doi":"https://doi.org/10.21437/interspeech.2015-107","title":"Enhanced speaker diarization with detection of backchannels using eye-gaze information in poster conversations","display_name":"Enhanced speaker diarization with detection of backchannels using eye-gaze information in poster conversations","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2402441703","doi":"https://doi.org/10.21437/interspeech.2015-107","mag":"2402441703"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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":"middle","author":{"id":"https://openalex.org/A5057581476","display_name":"Katsuya Takanashi","orcid":"https://orcid.org/0000-0001-6827-4807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsuya Takanashi","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":"3086","last_page":"3090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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":0.9986000061035156,"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":0.992900013923645,"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":0.9922999739646912,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8637140989303589},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8222696781158447},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.784553050994873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548694610595703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6183238625526428},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.590647280216217},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49948668479919434},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4456103444099426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38641834259033203},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15498217940330505},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1337776780128479}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8637140989303589},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8222696781158447},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.784553050994873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548694610595703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6183238625526428},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.590647280216217},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49948668479919434},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4456103444099426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38641834259033203},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15498217940330505},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1337776780128479},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W33176171","https://openalex.org/W58692019","https://openalex.org/W165173277","https://openalex.org/W1502693945","https://openalex.org/W1566669007","https://openalex.org/W1592567216","https://openalex.org/W1905952057","https://openalex.org/W1964725106","https://openalex.org/W1985479696","https://openalex.org/W1991123335","https://openalex.org/W2003522884","https://openalex.org/W2025905156","https://openalex.org/W2039206676","https://openalex.org/W2039842384","https://openalex.org/W2093442376","https://openalex.org/W2098013184","https://openalex.org/W2103621378","https://openalex.org/W2113638573","https://openalex.org/W2118748593","https://openalex.org/W2125336414","https://openalex.org/W2129770175","https://openalex.org/W2141398670","https://openalex.org/W2148613904","https://openalex.org/W2149653219","https://openalex.org/W2153842971","https://openalex.org/W2153994037","https://openalex.org/W2159229843","https://openalex.org/W2159591770","https://openalex.org/W2164216318","https://openalex.org/W2171757151","https://openalex.org/W2293592193","https://openalex.org/W2401047175","https://openalex.org/W2404408055","https://openalex.org/W2915347754"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2161294397","https://openalex.org/W2012644758","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"],"abstract_inverted_index":{"We":[0],"propose":[1],"multi-modal":[2,47],"speaker":[3,110],"diarization":[4,66,91],"using":[5],"acoustic":[6,43],"and":[7,39,75,96],"eye-gaze":[8,61,85],"information":[9,14,44,86],"in":[10,19,79],"poster":[11,81,115],"conversations.":[12],"Eye-gaze":[13],"plays":[15],"an":[16],"important":[17],"role":[18],"turn-taking,":[20],"thus":[21],"it":[22],"is":[23,99],"useful":[24],"for":[25],"predicting":[26],"speech":[27],"activity.":[28],"In":[29],"this":[30],"paper,":[31],"a":[32],"variety":[33],"of":[34,90],"eyegaze":[35],"features":[36],"are":[37],"elaborated":[38],"combined":[40],"with":[41],"the":[42,46,65,104],"by":[45,68],"integration":[48],"model.":[49],"Moreover,":[50],"we":[51],"introduce":[52],"another":[53],"model":[54],"to":[55,88,103],"detect":[56],"backchannels,":[57],"which":[58],"involve":[59],"different":[60],"behaviors.":[62],"This":[63],"enhances":[64],"result":[67],"filtering":[69],"meaningful":[70],"utterances":[71],"such":[72],"as":[73],"questions":[74],"comments.":[76],"Experimental":[77],"evaluations":[78],"real":[80],"sessions":[82],"demonstrate":[83],"that":[84],"contributes":[87],"improvement":[89],"accuracy":[92],"under":[93],"noisy":[94],"environments,":[95],"its":[97],"weight":[98],"automatically":[100],"determined":[101],"according":[102],"Signal-toNoise":[105],"Ratio":[106],"(SNR).":[107],"Index":[108],"Terms:":[109],"diarization,":[111],"backchannel,":[112],"multi-modal,":[113],"eye-gaze,":[114],"conversation":[116]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
