{"id":"https://openalex.org/W2895434601","doi":"https://doi.org/10.1145/3242969.3242994","title":"Evaluation of Real-time Deep Learning Turn-taking Models for Multiple Dialogue Scenarios","display_name":"Evaluation of Real-time Deep Learning Turn-taking Models for Multiple Dialogue Scenarios","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2895434601","doi":"https://doi.org/10.1145/3242969.3242994","mag":"2895434601"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3242994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3242969.3242994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3242969.3242994","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3242969.3242994","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Divesh Lala","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"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":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","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":["Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087376659"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":2.5385,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91924366,"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":"78","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8477901220321655},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8456307053565979},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.6206386685371399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557352304458618},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5317906737327576},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5206222534179688},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5138580799102783},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4595867693424225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39952173829078674},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3583155870437622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477901220321655},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8456307053565979},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.6206386685371399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557352304458618},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5317906737327576},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5206222534179688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5138580799102783},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4595867693424225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39952173829078674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3583155870437622},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3242969.3242994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3242969.3242994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3242969.3242994","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3242969.3242994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3242969.3242994","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3242969.3242994","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2281142962","display_name":null,"funder_award_id":"JPMJER1401","funder_id":"https://openalex.org/F4320338112","funder_display_name":"Exploratory Research for Advanced Technology"}],"funders":[{"id":"https://openalex.org/F4320338112","display_name":"Exploratory Research for Advanced Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2895434601.pdf","grobid_xml":"https://content.openalex.org/works/W2895434601.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W58692019","https://openalex.org/W1614298861","https://openalex.org/W1677182931","https://openalex.org/W1832693441","https://openalex.org/W2013987183","https://openalex.org/W2067097374","https://openalex.org/W2067348796","https://openalex.org/W2146486095","https://openalex.org/W2147934395","https://openalex.org/W2162634167","https://openalex.org/W2401047175","https://openalex.org/W2583914620","https://openalex.org/W2745949735","https://openalex.org/W2746424190","https://openalex.org/W2748406667","https://openalex.org/W2748416658","https://openalex.org/W2767461737","https://openalex.org/W2786387151","https://openalex.org/W2889445100","https://openalex.org/W2890197052","https://openalex.org/W2963093689"],"related_works":["https://openalex.org/W2228992124","https://openalex.org/W2613954729","https://openalex.org/W3130118443","https://openalex.org/W1955947659","https://openalex.org/W2759378137","https://openalex.org/W2376974064","https://openalex.org/W3188579947","https://openalex.org/W4289529495","https://openalex.org/W4386695291","https://openalex.org/W2355699586"],"abstract_inverted_index":{"The":[0,18],"task":[1],"of":[2,14,30,54,77,83,87,132,200],"identifying":[3],"when":[4],"to":[5,26,35,43,117,186,203],"take":[6],"a":[7,47,60,65,74,93,121,129,146,176,180,209],"conversational":[8],"turn":[9],"is":[10,42,183,189],"an":[11],"important":[12],"function":[13],"spoken":[15],"dialogue":[16,55,88],"systems.":[17],"turn-taking":[19,119,148],"system":[20],"should":[21],"also":[22,195],"ideally":[23],"be":[24],"able":[25],"handle":[27],"many":[28,52],"types":[29,53,86],"dialogue,":[31],"from":[32],"structured":[33],"conversation":[34,79,187],"spontaneous":[36],"and":[37,90,134,138,192],"unstructured":[38],"discourse.":[39],"Our":[40,150],"goal":[41,71],"determine":[44],"how":[45],"much":[46],"generalized":[48,94,155],"model":[49,61,95,156,161,177],"trained":[50,62],"on":[51,59,179],"scenarios":[56,165],"would":[57],"improve":[58,140],"only":[63],"for":[64,162],"specific":[66],"scenario.":[67],"To":[68],"achieve":[69],"this":[70],"we":[72,102,111,125],"created":[73],"large":[75,181],"corpus":[76,182],"Wizard-of-Oz":[78],"data":[80],"which":[81,110,188],"consisted":[82],"several":[84],"different":[85],"sessions,":[89],"then":[91],"compared":[92],"with":[96],"scenario-specific":[97],"models.":[98],"For":[99],"our":[100,141,198],"evaluation":[101,201],"go":[103],"further":[104,139],"than":[105],"simply":[106],"reporting":[107],"conventional":[108],"metrics,":[109],"show":[112,152],"are":[113],"not":[114],"informative":[115,205],"enough":[116],"evaluate":[118],"in":[120,169,208],"real-time":[122,143,210],"system.":[123,211],"Instead,":[124],"process":[126],"results":[127,151],"using":[128,145],"performance":[130,144,206],"curve":[131],"latency":[133],"false":[135],"cut-in":[136],"rate,":[137],"model's":[142],"finite-state":[147],"machine.":[149],"that":[153,175,197],"the":[154,159],"greatly":[157],"outperformed":[158],"individual":[160],"attentive":[163],"listening":[164],"but":[166],"was":[167],"worse":[168],"job":[170],"interview":[171],"scenarios.":[172],"This":[173],"implies":[174],"based":[178],"better":[184],"suited":[185],"more":[190,204],"user-initiated":[191],"unstructured.":[193],"We":[194],"propose":[196],"method":[199],"leads":[202],"metrics":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}