{"id":"https://openalex.org/W2810525233","doi":"https://doi.org/10.21437/interspeech.2018-2124","title":"Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs","display_name":"Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2810525233","doi":"https://doi.org/10.21437/interspeech.2018-2124","mag":"2810525233"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.11461","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032447843","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":"https://openalex.org/A5091225228","display_name":"Gabriel Skantze","orcid":"https://orcid.org/0000-0002-8579-1790"},"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 Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042231269","display_name":"Naomi Harte","orcid":"https://orcid.org/0000-0002-9274-209X"},"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":["https://openalex.org/A5032447843"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":1.8615,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89055969,"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":"586","last_page":"590"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.8950622081756592},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8453657627105713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8194576501846313},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6839301586151123},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5782018899917603},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5676108002662659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5504834651947021},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.485400527715683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4438861906528473},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4251159429550171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33285871148109436},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08009651303291321},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07283365726470947}],"concepts":[{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.8950622081756592},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8453657627105713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194576501846313},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6839301586151123},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5782018899917603},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5676108002662659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5504834651947021},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.485400527715683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438861906528473},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4251159429550171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33285871148109436},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08009651303291321},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07283365726470947},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-2124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.11461","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.11461","pdf_url":"https://arxiv.org/pdf/1806.11461","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2810525233","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.11461v1","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1806.11461","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.11461","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.11461","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.11461","pdf_url":"https://arxiv.org/pdf/1806.11461","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2810525233.pdf","grobid_xml":"https://content.openalex.org/works/W2810525233.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W68208136","https://openalex.org/W316215934","https://openalex.org/W1494198834","https://openalex.org/W1566669007","https://openalex.org/W1608166496","https://openalex.org/W1932883564","https://openalex.org/W1985479696","https://openalex.org/W2001292406","https://openalex.org/W2008741806","https://openalex.org/W2026535637","https://openalex.org/W2067097374","https://openalex.org/W2067348796","https://openalex.org/W2085662862","https://openalex.org/W2100919116","https://openalex.org/W2129090275","https://openalex.org/W2153190547","https://openalex.org/W2239141610"],"related_works":["https://openalex.org/W2786387151","https://openalex.org/W1533504578","https://openalex.org/W2745949735","https://openalex.org/W2162634167","https://openalex.org/W2153190547","https://openalex.org/W2001292406","https://openalex.org/W1986532700","https://openalex.org/W2895434601","https://openalex.org/W2886091977","https://openalex.org/W3204492243","https://openalex.org/W3103733040","https://openalex.org/W1502349317","https://openalex.org/W2600556233","https://openalex.org/W2275246416","https://openalex.org/W3119755711","https://openalex.org/W3036400793","https://openalex.org/W2341088792","https://openalex.org/W2327991832","https://openalex.org/W2963794160","https://openalex.org/W2092497681"],"abstract_inverted_index":{"For":[0],"spoken":[1],"dialog":[2],"systems":[3,12],"to":[4,16,35,45,62,73,112,120],"conduct":[5],"fluid":[6],"conversational":[7],"interactions":[8],"with":[9],"users,":[10],"the":[11,43,83,105],"must":[13],"be":[14,25,32,110],"sensitive":[15],"turn-taking":[17,75,101],"cues":[18],"produced":[19],"by":[20],"a":[21,77,93],"user.":[22],"Models":[23],"should":[24],"designed":[26],"so":[27],"that":[28,115,143,160],"effective":[29],"decisions":[30,51,114],"can":[31,109],"made":[33,53],"as":[34],"when":[36],"it":[37],"is":[38,72],"appropriate,":[39],"or":[40],"not,":[41],"for":[42,89,132],"system":[44,84],"speak.":[46],"Traditional":[47],"end-of-turn":[48,121],"models,":[49],"where":[50,82],"are":[52,57,116],"at":[54,135],"utterance":[55],"end-points,":[56],"limited":[58,119],"in":[59,76,104,139],"their":[60],"ability":[61],"model":[63,74],"fast":[64],"turn-switches":[65],"and":[66,108,137],"overlap.":[67],"A":[68],"more":[69],"flexible":[70],"approach":[71],"continuous":[78,97],"manner":[79],"using":[80],"RNNs,":[81],"predicts":[85],"speech":[86],"probability":[87],"scores":[88],"discrete":[90],"frames":[91],"within":[92],"future":[94],"window.":[95],"The":[96],"predictions":[98,134],"represent":[99],"generalized":[100],"behaviors":[102],"observed":[103],"training":[106],"data":[107],"applied":[111],"make":[113],"not":[117],"just":[118],"detection.":[122],"In":[123],"this":[124],"paper,":[125],"we":[126],"investigate":[127],"optimal":[128],"speech-related":[129],"feature":[130],"sets":[131],"making":[133],"pauses":[136],"overlaps":[138],"conversation.":[140],"We":[141,158],"find":[142],"while":[144],"traditional":[145],"acoustic":[146],"features":[147,151],"perform":[148,153],"well,":[149],"part-of-speech":[150],"generally":[152],"worse":[154],"than":[155],"word":[156],"features.":[157],"show":[159],"our":[161],"current":[162],"models":[163],"outperform":[164],"previously":[165],"reported":[166],"baselines.":[167]},"counts_by_year":[{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
