{"id":"https://openalex.org/W7148349898","doi":"https://doi.org/10.1109/asru65441.2025.11434798","title":"Predictive ASR and Turn-taking Prediction at Once: Towards More Responsive Spoken Dialog System","display_name":"Predictive ASR and Turn-taking Prediction at Once: Towards More Responsive Spoken Dialog System","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148349898","doi":"https://doi.org/10.1109/asru65441.2025.11434798"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5052080737","display_name":"Ryo Fukuda","orcid":"https://orcid.org/0009-0005-6213-3241"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryo Fukuda","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042592085","display_name":"Takatomo Kano","orcid":"https://orcid.org/0000-0001-9693-3785"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takatomo Kano","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800196","display_name":"Yuya Chiba","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Chiba","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132803906","display_name":"Atsushi Ando","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052080737"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87555398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8460000157356262,"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":0.8460000157356262,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.017500000074505806,"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/feature","display_name":"Feature (linguistics)","score":0.3005000054836273},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.22990000247955322},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.22370000183582306},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.21410000324249268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.650600016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4000000059604645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.22990000247955322},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.22370000183582306},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.21410000324249268},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2134000062942505},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.19509999454021454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W9486812","https://openalex.org/W1533504578","https://openalex.org/W1583748115","https://openalex.org/W1608166496","https://openalex.org/W2064675550","https://openalex.org/W2072921909","https://openalex.org/W2137374537","https://openalex.org/W2153190547","https://openalex.org/W2166637769","https://openalex.org/W2745949735","https://openalex.org/W2786387151","https://openalex.org/W2888997666","https://openalex.org/W2889231094","https://openalex.org/W2962780374","https://openalex.org/W2963747517","https://openalex.org/W2973137193","https://openalex.org/W2980823180","https://openalex.org/W3094393093","https://openalex.org/W3097777922","https://openalex.org/W3112188842","https://openalex.org/W4297841778","https://openalex.org/W4297841817","https://openalex.org/W4385823309","https://openalex.org/W4392902922","https://openalex.org/W4402112402","https://openalex.org/W4402112431","https://openalex.org/W4402116591","https://openalex.org/W4405236381","https://openalex.org/W4408352728"],"related_works":[],"abstract_inverted_index":{"Spoken":[0],"dialog":[1],"systems":[2],"usually":[3],"wait":[4],"for":[5,20],"users":[6],"to":[7,26,44,98],"finish":[8],"speaking":[9],"before":[10],"generating":[11],"responses,":[12],"resulting":[13],"in":[14,116],"response":[15,23],"delays.":[16],"A":[17],"possible":[18],"solution":[19],"reducing":[21],"the":[22,33,100,104],"delay":[24],"is":[25,35],"predict":[27],"future":[28,65,90],"words":[29,127,131],"and/or":[30],"turn-ends":[31],"while":[32],"user":[34],"speaking.":[36],"To":[37],"realize":[38],"this,":[39],"we":[40],"propose":[41],"a":[42,113],"method":[43],"jointly":[45],"perform":[46],"predictive":[47],"automatic":[48],"speech":[49,63],"recognition":[50],"and":[51,61,68,81,88],"turn-taking":[52,117,123],"prediction.":[53,118],"Our":[54],"model":[55,111,115],"receives":[56],"partial":[57,86],"utterances":[58,87],"as":[59],"input":[60],"performs":[62],"recognition,":[64],"word":[66],"prediction,":[67],"turntaking":[69,76],"prediction":[70,77,124],"via":[71],"autoregressive":[72],"decoding.":[73],"It":[74],"enables":[75],"based":[78],"on":[79,103,125],"prosodic":[80],"linguistic":[82,91],"cues":[83],"of":[84],"observed":[85],"predicted":[89,126],"cues.":[92],"We":[93,119],"also":[94],"incorporate":[95],"dialogue":[96],"contexts":[97],"improve":[99],"performance.":[101],"Experiments":[102],"Switchboard":[105],"corpus":[106],"showed":[107],"that":[108,121],"our":[109],"multi-task":[110],"outperforms":[112],"single-task":[114],"found":[120],"conditioning":[122],"improved":[128],"performance":[129],"when":[130],"were":[132],"correctly":[133],"predicted.":[134]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
