{"id":"https://openalex.org/W4385822387","doi":"https://doi.org/10.21437/interspeech.2023-578","title":"Multimodal Turn-Taking Model Using Visual Cues for End-of-Utterance Prediction in Spoken Dialogue Systems","display_name":"Multimodal Turn-Taking Model Using Visual Cues for End-of-Utterance Prediction in Spoken Dialogue Systems","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822387","doi":"https://doi.org/10.21437/interspeech.2023-578"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-578","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","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/A5092639572","display_name":"Fuma Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fuma Kurata","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065997585","display_name":"Mao Saeki","orcid":"https://orcid.org/0000-0002-1825-2236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao Saeki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007054949","display_name":"Shinya Fujie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinya Fujie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078242198","display_name":"Yoichi Matsuyama","orcid":"https://orcid.org/0000-0003-0282-6482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoichi Matsuyama","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092639572"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2054,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83225881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2658","last_page":"2662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9976999759674072,"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":0.9976999759674072,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9603999853134155,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9186000227928162,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.857474684715271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345761060714722},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.5747057199478149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5219813585281372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008983612060547},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.457955926656723},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3806728422641754},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3381742537021637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3350663185119629},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.19145354628562927},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13220888376235962},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.11336123943328857}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.857474684715271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345761060714722},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.5747057199478149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5219813585281372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008983612060547},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.457955926656723},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3806728422641754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3381742537021637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3350663185119629},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.19145354628562927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13220888376235962},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.11336123943328857}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-578","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2903456225","https://openalex.org/W1978877097","https://openalex.org/W3208962307","https://openalex.org/W2595453317","https://openalex.org/W3182597358","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1587348481","https://openalex.org/W2558461613"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
