{"id":"https://openalex.org/W2891104250","doi":"https://doi.org/10.1109/icassp.2018.8461470","title":"Audio-Visual Conversation Analysis by Smart Posterboard and Humanoid Robot","display_name":"Audio-Visual Conversation Analysis by Smart Posterboard and Humanoid Robot","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891104250","doi":"https://doi.org/10.1109/icassp.2018.8461470","mag":"2891104250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058775745","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0002-2929-2559"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Inoue","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087376659","display_name":"Divesh Lala","orcid":"https://orcid.org/0009-0005-3181-6410"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Divesh Lala","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057581476","display_name":"Katsuya Takanashi","orcid":"https://orcid.org/0000-0001-6827-4807"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuya Takanashi","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6573","last_page":"6577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10860","display_name":"Speech and Audio Processing","score":0.9632999897003174,"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/T12290","display_name":"Human Motion and Animation","score":0.9315999746322632,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7640527486801147},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7049182653427124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.698952317237854},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6485372185707092},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5307586193084717},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43215397000312805},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39073508977890015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35871803760528564},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35518890619277954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.353343665599823},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15372002124786377},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13163724541664124}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7640527486801147},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7049182653427124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698952317237854},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6485372185707092},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5307586193084717},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43215397000312805},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39073508977890015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35871803760528564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35518890619277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.353343665599823},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15372002124786377},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13163724541664124}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":32,"referenced_works":["https://openalex.org/W58692019","https://openalex.org/W165173277","https://openalex.org/W1943228824","https://openalex.org/W2025905156","https://openalex.org/W2044924490","https://openalex.org/W2102759648","https://openalex.org/W2103621378","https://openalex.org/W2113638573","https://openalex.org/W2278865652","https://openalex.org/W2290365000","https://openalex.org/W2293592193","https://openalex.org/W2402441703","https://openalex.org/W2407280320","https://openalex.org/W2513807562","https://openalex.org/W2554972835","https://openalex.org/W2565288664","https://openalex.org/W2565542385","https://openalex.org/W2594833372","https://openalex.org/W2747602812","https://openalex.org/W2748406667","https://openalex.org/W2750497738","https://openalex.org/W2886370553","https://openalex.org/W6602347453","https://openalex.org/W6640526923","https://openalex.org/W6656914388","https://openalex.org/W6695220876","https://openalex.org/W6697110557","https://openalex.org/W6713276338","https://openalex.org/W6713734929","https://openalex.org/W6730089581","https://openalex.org/W6731110927","https://openalex.org/W6754309187"],"related_works":["https://openalex.org/W1968552888","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W2772323916","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W2378167147","https://openalex.org/W3210777354","https://openalex.org/W2281307425","https://openalex.org/W2765333006"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"addresses":[2],"audio-visual":[3,57],"signal":[4],"processing":[5],"for":[6],"conversation":[7],"analysis,":[8],"which":[9],"involves":[10],"multi-modal":[11,32],"behavior":[12,121],"detection":[13,81,122],"and":[14,34,48,79,85,103,125,133],"mental-state":[15],"recognition.":[16],"We":[17,64,92],"have":[18],"investigated":[19],"prediction":[20],"of":[21,82,105],"turn-taking":[22],"by":[23,60],"the":[24,38,75,101,113,129,135,138],"audience":[25],"in":[26,70],"a":[27,94],"poster":[28],"session":[29],"from":[30],"their":[31],"behaviors,":[33],"found":[35],"out":[36],"that":[37,111],"eye-gaze":[39,62,136],"provides":[40],"an":[41],"important":[42,140],"cue":[43],"compared":[44],"with":[45,100],"head":[46],"nodding":[47,86],"verbal":[49],"backchannels.":[50],"finding":[52],"has":[53],"been":[54],"applied":[55],"to":[56,98],"speaker":[58],"diarization":[59],"combining":[61],"information.":[63],"are":[65],"now":[66],"investigating":[67],"engagement":[68,106,130],"recognition":[69,131],"human-robot":[71],"interaction":[72],"based":[73,89],"on":[74,90],"same":[76],"scheme.":[77],"Robust":[78],"realtime":[80],"laughing,":[83],"backchannels":[84],"is":[87,117,123,137],"realized":[88],"LSTM-CTC.":[91],"introduce":[93],"latent":[95,114],"\u201ccharacter\u201d":[96],"model":[97,116],"cope":[99],"subjectivity":[102],"variations":[104],"annotations.":[107],"Experimental":[108],"evaluations":[109],"demonstrate":[110],"(1)":[112],"character":[115],"effective,":[118],"(2)":[119],"automatic":[120],"robust":[124],"does":[126],"not":[127],"degrade":[128],"accuracy,":[132],"(3)":[134],"most":[139],"feature":[141],"among":[142],"others.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
