{"id":"https://openalex.org/W2888997666","doi":"https://doi.org/10.1145/3242969.3242997","title":"Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs","display_name":"Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2888997666","doi":"https://doi.org/10.1145/3242969.3242997","mag":"2888997666"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3242997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3242997","pdf_url":null,"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.10785","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matthew Roddy","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Matthew Roddy","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gabriel Skantze","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gabriel Skantze","raw_affiliation_strings":["KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Naomi Harte","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Naomi Harte","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":1.0153,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.82759472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7675999999046326},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5666999816894531},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49619999527931213},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.4406000077724457},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3547999858856201},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.31790000200271606},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.31769999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791000008583069},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7675999999046326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647599995136261},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3242969.3242997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3242997","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:1808.10785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.10785","pdf_url":"https://arxiv.org/pdf/1808.10785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:tara.tcd.ie:2262/89623","is_oa":false,"landing_page_url":"http://hdl.handle.net/2262/89623","pdf_url":null,"source":{"id":"https://openalex.org/S4306400387","display_name":"Trinity's Access to Research Output (TARA) (Trinity College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205274468","host_organization_name":"Trinity College Dublin","host_organization_lineage":["https://openalex.org/I205274468"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.10785","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.10785","pdf_url":"https://arxiv.org/pdf/1808.10785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2001292406","https://openalex.org/W2027624334","https://openalex.org/W2067097374","https://openalex.org/W2085662862","https://openalex.org/W2116985048","https://openalex.org/W2118142207","https://openalex.org/W2239141610","https://openalex.org/W2745949735","https://openalex.org/W2963747517","https://openalex.org/W4248634141"],"related_works":[],"abstract_inverted_index":{"In":[0],"human":[1],"conversational":[2],"interactions,":[3],"turn-taking":[4,34,84,100],"exchanges":[5],"can":[6,20,80,92],"be":[7,49,81,93],"coordinated":[8],"using":[9],"cues":[10,29],"from":[11,30],"multiple":[12],"modalities.":[13],"To":[14],"design":[15,52],"spoken":[16],"dialog":[17],"systems":[18],"that":[19,38,70,89],"conduct":[21],"fluid":[22],"interactions":[23],"it":[24],"is":[25,40],"desirable":[26],"to":[27,57,95],"incorporate":[28,96],"separate":[31,61,77],"modalities":[32,47,59],"into":[33,99],"models.":[35,101],"We":[36,51,86],"propose":[37],"there":[39],"an":[41],"appropriate":[42],"temporal":[43,78],"granularity":[44],"at":[45,60,76],"which":[46],"should":[48],"modeled.":[50],"a":[53,64],"multiscale":[54],"RNN":[55],"architecture":[56],"model":[58],"timescales":[62],"in":[63],"continuous":[65],"manner.":[66],"Our":[67],"results":[68],"show":[69,88],"modeling":[71],"linguistic":[72],"and":[73],"acoustic":[74],"features":[75,98],"rates":[79],"beneficial":[82],"for":[83],"modeling.":[85],"also":[87],"our":[90],"approach":[91],"used":[94],"gaze":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2018-09-07T00:00:00"}