{"id":"https://openalex.org/W58692019","doi":"https://doi.org/10.21437/interspeech.2010-571","title":"Turn-alignment using eye-gaze and speech in conversational interaction","display_name":"Turn-alignment using eye-gaze and speech in conversational interaction","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W58692019","doi":"https://doi.org/10.21437/interspeech.2010-571","mag":"58692019"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-571","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5016722544","display_name":"Kristiina Jokinen","orcid":"https://orcid.org/0000-0003-1229-239X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kristiina Jokinen","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016312460","display_name":"Kazuaki Harada","orcid":"https://orcid.org/0009-0008-2558-0642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuaki Harada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109009818","display_name":"Masafumi Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masafumi Nishida","raw_affiliation_strings":["Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086759974","display_name":"Seiichi Yamamoto","orcid":"https://orcid.org/0000-0002-1280-0043"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiichi Yamamoto","raw_affiliation_strings":["Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1276,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94995387,"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":"2018","last_page":"2021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9993000030517578,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9900000095367432,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.8452446460723877},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.7377453446388245},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6829866170883179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6735585331916809},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5614768862724304},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5059410929679871},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.4786290228366852},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4472884237766266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3880220651626587},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35294869542121887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31454920768737793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29043516516685486},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.23265796899795532}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8452446460723877},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.7377453446388245},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6829866170883179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6735585331916809},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5614768862724304},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5059410929679871},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4786290228366852},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4472884237766266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3880220651626587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35294869542121887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31454920768737793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29043516516685486},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.23265796899795532},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-571","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W91267029","https://openalex.org/W614048249","https://openalex.org/W1563178652","https://openalex.org/W1570448133","https://openalex.org/W1855240845","https://openalex.org/W1978874520","https://openalex.org/W1985479696","https://openalex.org/W2015111784","https://openalex.org/W2035366352","https://openalex.org/W2038219465","https://openalex.org/W2055749882","https://openalex.org/W2096284813","https://openalex.org/W2128970689","https://openalex.org/W2131554716","https://openalex.org/W2143542324","https://openalex.org/W2161299247","https://openalex.org/W2969324886"],"related_works":["https://openalex.org/W2892813288","https://openalex.org/W2170584777","https://openalex.org/W2141666434","https://openalex.org/W2161294397","https://openalex.org/W2012644758","https://openalex.org/W2789189004","https://openalex.org/W83540058","https://openalex.org/W4389009518","https://openalex.org/W4295682112","https://openalex.org/W3143450176"],"abstract_inverted_index":{"Abstract":[0],"Spoken":[1],"interactions":[2,267],"are":[3,16,81,424,515],"known":[4],"for":[5,63,232,246,254],"accurate":[6],"timing":[7],"and":[8,13,25,40,43,67,87,135,141,176,180,182,207,213,257,277,283,295,388,396,399,414,418,422,434,451,457,474,505,513,558,563,573,579,596],"alignment":[9,279,560],"between":[10,36,133,386,503],"interlocutors:":[11],"turn-taking":[12,59,110,156,202,276,458,468,557],"topic":[14],"flow":[15],"managed":[17],"in":[18,70,84,117,155,178,204,216,266,280,306,315,328,335,377,390,405,518,565,576,589],"a":[19,74,217,291,372],"manner":[20],"that":[21,78,196,208,305,334,442,478,500],"provides":[22],"conversational":[23,136,255,270],"fluency":[24],"smooth":[26],"progress":[27],"of":[28,98,115,147,198,211,229,288,320,371,420,429,467,540,561],"the":[29,34,37,61,96,159,166,172,183,191,209,286,309,351,369,378,384,393,448,465,471,475,484,488,501,538,541,554,559],"task.":[30],"This":[31],"paper":[32,546],"studies":[33],"relation":[35,385],"interlocutors\u2019":[38,449],"eye-gaze":[39,79,116,134,230,244,261,278,289,387,479,512,530],"spoken":[41],"utterances,":[42],"describes":[44],"our":[45,299,409,438,571],"experiments":[46,53,462],"on":[47,58,275,285,412,556],"turn":[48,85,167,344,395,406,519],"alignment.":[49],"We":[50,436,551,568],"conducted":[51],"classification":[52,466,489],"by":[54,168],"Support":[55],"Vector":[56],"Machine":[57],"using":[60,470],"features":[62,80,94,398,459,473,507],"dialogue":[64,397,430,440,454,491],"act,":[65],"eye-gaze,":[66,105,456],"speech":[68,93,108,212,402,423,480,506,514,536,562,574],"prosody":[69],"conversation":[71],"data.":[72],"As":[73],"result,":[75],"we":[76,303],"demonstrated":[77],"important":[82,91,154,314,366,516,534],"signals":[83,517],"management,":[86,520],"seem":[88],"even":[89],"more":[90,533],"than":[92,324,527,535],"when":[95,342,537],"intention":[97,539],"utterances":[99],"is":[100,152,194,327,353,365,381,443,497,508,524,543,547],"clear.":[101,544],"Index":[102],"Terms":[103],":":[104],"dialogue,":[106],"interaction,":[107],"analysis,":[109],"1.":[111],"Introduction":[112],"The":[113,374,461,545],"role":[114,287],"fluent":[118],"communication":[119],"has":[120,129],"long":[121],"since":[122],"been":[123,237],"acknowledged":[124],"([2];":[125],"[7]).":[126],"Previous":[127],"research":[128,273,380,410,555],"established":[130],"close":[131],"relations":[132],"feedback":[137],"([3]),":[138],"building":[139],"trust":[140],"rapport,":[142],"as":[143,145,290,549,582,584],"well":[144,583],"focus":[146],"shared":[148],"attention":[149],"([15]).":[150],"Eye-gaze":[151],"also":[153,236,498],"signalling:":[157],"usually":[158],"interlocutors":[160],"signal":[161],"their":[162,345,356,522,587],"wish":[163],"to":[164,171,189,263,293,347,358,367,382,447,532,598],"give":[165],"gazing":[169],"up":[170],"interlocutor,":[173],"leaning":[174],"back,":[175],"dropping":[177],"pitch":[179],"loudness,":[181],"partner":[184],"can,":[185],"accordingly,":[186],"start":[187],"preparing":[188],"take":[190],"turn.":[192],"There":[193],"evidence":[195],"lack":[197],"eye":[199],"contact":[200],"decreases":[201],"efficiency":[203],"video-conferencing":[205],"([16]),":[206],"coupling":[210],"gaze":[214,252,370,421,504,564],"streams":[215],"word":[218],"acquisition":[219],"task":[220],"can":[221],"improve":[222],"performance":[223],"significantly":[224,482],"([11]).":[225],"Several":[226],"computational":[227],"models":[228],"behaviour":[231],"artificial":[233],"agents":[234],"have":[235],"designed.":[238],"For":[239],"instance,":[240],"[9]":[241],"describe":[242,553],"an":[243,260,361],"model":[245,262],"believable":[247],"virtual":[248,336],"humans,":[249],"[13]":[250],"demonstrate":[251],"modelling":[253],"engage-ment,":[256],"[10]":[258],"built":[259],"ground":[264],"information":[265,481,493],"with":[268,330,426,445,453,464,487,490],"embodied":[269],"agents.":[271],"Our":[272],"focuses":[274],"natural":[281],"dialogues":[282,308],"especially":[284],"means":[292],"coordinate":[294],"control":[296],"turn-taking.":[297],"In":[298],"previous":[300],"work":[301],"[5,6]":[302],"noticed":[304,333],"multi-party":[307],"participants":[310],"head":[311,338,357],"movement":[312],"was":[313],"signalling":[316],"turn-taking,":[317],"maybe":[318],"because":[319],"its":[321],"greater":[322],"visibility":[323],"eye-gaze.":[325],"(This":[326],"agreement":[329],"[12],":[331],"who":[332],"environments,":[337],"tracking":[339],"seems":[340,531],"sufficient":[341],"people":[343],"heads":[346],"look":[348,359],"but":[349,521],"if":[350],"person":[352],"not":[354,509],"turning":[355],"at":[360],"object,":[362],"then":[363,569],"eye-tracking":[364],"discern":[368],"person.)":[373],"main":[375],"objective":[376],"current":[379],"explore":[383],"speech,":[389,450],"particular,":[391],"how":[392],"annotated":[394,452],"automatically":[400],"recognized":[401],"properties":[403],"affect":[404],"management.":[407],"Methodologically":[408],"relies":[411],"experimentation":[413],"observation:":[415],"signal-level":[416],"measurements":[417],"analysis":[419,575],"combined":[425],"human-level":[427],"observation":[428],"events":[431,469],"(dialogue":[432],"acts":[433],"turn-taking).":[435],"use":[437],"three-party":[439],"data":[441,572],"analysed":[444,472],"respect":[446],"acts,":[455],"[6].":[460],"deal":[463],"results":[476,581],"show":[477],"improves":[483],"accuracy":[485],"compared":[486],"act":[492],"only.":[494],"However,":[495],"what":[496],"interesting":[499],"difference":[502],"significant,":[510],"i.e.":[511],"effect":[523],"parallel":[525],"rather":[526],"complementary.":[528],"Moreover,":[529],"utterance":[542],"structured":[548],"follows.":[550],"first":[552],"Section":[566,577,590,592],"2.":[567],"present":[570],"3,":[578],"experimental":[580],"discussion":[585],"concerning":[586],"importance":[588],"4.":[591],"5":[593],"draws":[594],"conclusions":[595],"points":[597],"future":[599],"research.":[600]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}