{"id":"https://openalex.org/W7116839081","doi":"https://doi.org/10.1007/978-981-95-2382-5_15","title":"Towards Improving Turn-Taking in\u00a0Social Robots Using Visual-Only Voice Activity Detection in\u00a0Multimodal Dialogue Systems","display_name":"Towards Improving Turn-Taking in\u00a0Social Robots Using Visual-Only Voice Activity Detection in\u00a0Multimodal Dialogue Systems","publication_year":2025,"publication_date":"2025-12-23","ids":{"openalex":"https://openalex.org/W7116839081","doi":"https://doi.org/10.1007/978-981-95-2382-5_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-2382-5_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-2382-5_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5024999247","display_name":"Antonio Cano","orcid":null},"institutions":[{"id":"https://openalex.org/I110220311","display_name":"Wako University","ror":"https://ror.org/05n7t1e46","country_code":"JP","type":"education","lineage":["https://openalex.org/I110220311"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I79238269","display_name":"Universidad de Sevilla","ror":"https://ror.org/03yxnpp24","country_code":"ES","type":"education","lineage":["https://openalex.org/I79238269"]},{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES","JP"],"is_corresponding":true,"raw_author_name":"Antonio Cano","raw_affiliation_strings":["4i Intelligent Insights, Sevilla, 41092, Spain","Universidad Pablo de Olavide, 41013, Sevilla, Spain","Wako Saitama, 351-0188, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0435-4987","affiliations":[{"raw_affiliation_string":"4i Intelligent Insights, Sevilla, 41092, Spain","institution_ids":["https://openalex.org/I79238269"]},{"raw_affiliation_string":"Universidad Pablo de Olavide, 41013, Sevilla, Spain","institution_ids":["https://openalex.org/I95013407"]},{"raw_affiliation_string":"Wako Saitama, 351-0188, Japan","institution_ids":["https://openalex.org/I110220311","https://openalex.org/I4210110652"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guillermo Perez","orcid":"https://orcid.org/0000-0002-8358-996X"},"institutions":[{"id":"https://openalex.org/I79238269","display_name":"Universidad de Sevilla","ror":"https://ror.org/03yxnpp24","country_code":"ES","type":"education","lineage":["https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Guillermo Perez","raw_affiliation_strings":["4i Intelligent Insights, Sevilla, 41092, Spain"],"raw_orcid":"https://orcid.org/0000-0002-8358-996X","affiliations":[{"raw_affiliation_string":"4i Intelligent Insights, Sevilla, 41092, Spain","institution_ids":["https://openalex.org/I79238269","https://openalex.org/I79238269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121031785","display_name":"Luis Merino","orcid":null},"institutions":[{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Merino","raw_affiliation_strings":["Universidad Pablo de Olavide, 41013, Sevilla, Spain"],"raw_orcid":"https://orcid.org/0000-0003-4927-8647","affiliations":[{"raw_affiliation_string":"Universidad Pablo de Olavide, 41013, Sevilla, Spain","institution_ids":["https://openalex.org/I95013407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I110220311","display_name":"Wako University","ror":"https://ror.org/05n7t1e46","country_code":"JP","type":"education","lineage":["https://openalex.org/I110220311"]},{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I79238269","display_name":"Universidad de Sevilla","ror":"https://ror.org/03yxnpp24","country_code":"ES","type":"education","lineage":["https://openalex.org/I79238269"]},{"id":"https://openalex.org/I95013407","display_name":"Universidad Pablo de Olavide","ror":"https://ror.org/02z749649","country_code":"ES","type":"education","lineage":["https://openalex.org/I95013407"]}],"countries":["ES","JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["4i Intelligent Insights, Sevilla, 41092, Spain","Universidad Pablo de Olavide, 41013, Sevilla, Spain","Wako Saitama, 351-0188, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3191-6818","affiliations":[{"raw_affiliation_string":"4i Intelligent Insights, Sevilla, 41092, Spain","institution_ids":["https://openalex.org/I79238269"]},{"raw_affiliation_string":"Universidad Pablo de Olavide, 41013, Sevilla, Spain","institution_ids":["https://openalex.org/I95013407"]},{"raw_affiliation_string":"Wako Saitama, 351-0188, Japan","institution_ids":["https://openalex.org/I110220311","https://openalex.org/I4210110652"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024999247"],"corresponding_institution_ids":["https://openalex.org/I110220311","https://openalex.org/I4210110652","https://openalex.org/I79238269","https://openalex.org/I95013407"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84276475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8076000213623047,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.8076000213623047,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12031","display_name":"Speech and dialogue systems","score":0.0738999992609024,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.020500000566244125,"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/robot","display_name":"Robot","score":0.7166000008583069},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6315000057220459},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4968000054359436},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46939998865127563},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.45410001277923584},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.4156999886035919},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.41370001435279846},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3732999861240387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8615999817848206},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7166000008583069},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206999778747559},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4968000054359436},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46939998865127563},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.45410001277923584},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.41370001435279846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38670000433921814},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-2382-5_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-2382-5_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1908118577","https://openalex.org/W2002979515","https://openalex.org/W2017835752","https://openalex.org/W2029199293","https://openalex.org/W2065257586","https://openalex.org/W2323437298","https://openalex.org/W2512215050","https://openalex.org/W2791548316","https://openalex.org/W2793493229","https://openalex.org/W2803193013","https://openalex.org/W2917987043","https://openalex.org/W2963524571","https://openalex.org/W2970250044","https://openalex.org/W3016011581","https://openalex.org/W3094061997","https://openalex.org/W3119269912","https://openalex.org/W3196984997","https://openalex.org/W3197459407","https://openalex.org/W3200575128","https://openalex.org/W4213199077","https://openalex.org/W4297841817","https://openalex.org/W4312268709","https://openalex.org/W4312827348","https://openalex.org/W4366201642","https://openalex.org/W4372317224","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4386850926","https://openalex.org/W4389282358","https://openalex.org/W4391021764","https://openalex.org/W4401414238","https://openalex.org/W4402754289","https://openalex.org/W4405778816","https://openalex.org/W4410297768","https://openalex.org/W4411113049","https://openalex.org/W4413188229"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-12-23T00:00:00"}
