{"id":"https://openalex.org/W4415432641","doi":"https://doi.org/10.21437/interspeech.2025-2660","title":"Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems","display_name":"Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432641","doi":"https://doi.org/10.21437/interspeech.2025-2660"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.07518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085921759","display_name":"Mikey Elmers","orcid":"https://orcid.org/0000-0002-3929-788X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikey Elmers","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058775745","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0002-2929-2559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koji Inoue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087376659","display_name":"Divesh Lala","orcid":"https://orcid.org/0009-0005-3181-6410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Divesh Lala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3015","last_page":"3019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.839900016784668},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5737000107765198},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.839900016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389999985694885},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5315999984741211},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421999990940094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2705000042915344}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2660","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.07518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07518","pdf_url":"https://arxiv.org/pdf/2507.07518","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.07518","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.07518","pdf_url":"https://arxiv.org/pdf/2507.07518","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Turn-taking":[0],"is":[1,37,52],"a":[2,67,74],"fundamental":[3],"component":[4],"of":[5,34,76,97],"spoken":[6,126],"dialogue,":[7],"however":[8],"conventional":[9],"studies":[10],"mostly":[11],"involve":[12],"dyadic":[13],"settings.":[14],"This":[15,51,102],"work":[16,117],"focuses":[17],"on":[18,66,84],"applying":[19],"voice":[20,42],"activity":[21,43],"projection":[22],"(VAP)":[23],"to":[24,38,56],"predict":[25,39],"upcoming":[26],"turn-taking":[27,111,123],"in":[28,112],"triadic":[29,60,69,85,113,121],"multi-party":[30],"scenarios.":[31,115],"The":[32],"goal":[33],"VAP":[35,58,82,106,122],"models":[36,65,92],"the":[40,53,81,88,95,100],"future":[41],"for":[44,90,110],"each":[45],"speaker":[46],"utilizing":[47],"only":[48],"acoustic":[49],"data.":[50],"first":[54],"study":[55,103],"extend":[57],"into":[59,125],"conversation.":[61],"We":[62,78],"trained":[63,83],"multiple":[64],"Japanese":[68],"dataset":[70],"where":[71],"participants":[72],"discussed":[73],"variety":[75],"topics.":[77],"found":[79],"that":[80,94,105],"conversation":[86,98],"outperformed":[87],"baseline":[89],"all":[91],"but":[93],"type":[96],"affected":[99],"accuracy.":[101],"establishes":[104],"can":[107],"be":[108],"used":[109],"dialogue":[114,127],"Future":[116],"will":[118],"incorporate":[119],"this":[120],"model":[124],"systems.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-23T00:00:00"}