{"id":"https://openalex.org/W4416800198","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249350","title":"Constructing an In-the-Wild Spoken Dialogue Dataset Based on Youtube Dialogue Videos","display_name":"Constructing an In-the-Wild Spoken Dialogue Dataset Based on Youtube Dialogue Videos","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800198","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249350"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5038536046","display_name":"Yuki Sato","orcid":"https://orcid.org/0000-0001-8974-2059"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Sato","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716048","display_name":"Sanae Yamashita","orcid":"https://orcid.org/0009-0002-5994-4703"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sanae Yamashita","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Keio University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004045909","display_name":"Ryuichiro Higashinaka","orcid":"https://orcid.org/0000-0002-6994-3977"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichiro Higashinaka","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17671597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7149999737739563,"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":0.7149999737739563,"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/T12128","display_name":"AI in Service Interactions","score":0.034299999475479126,"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/T14236","display_name":"Educational Tools and Methods","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6534000039100647},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.28369998931884766},{"id":"https://openalex.org/keywords/spoken-word","display_name":"Spoken word","score":0.2313999980688095},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.21320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860000133514404},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6534000039100647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6090999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C504583287","wikidata":"https://www.wikidata.org/wiki/Q1428637","display_name":"Spoken word","level":3,"score":0.2313999980688095},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.21320000290870667},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.20919999480247498}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1526236009","https://openalex.org/W2007889078","https://openalex.org/W2015866473","https://openalex.org/W2166637769","https://openalex.org/W2527515520","https://openalex.org/W2786387151","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W3198694222","https://openalex.org/W4226061996","https://openalex.org/W4239187549","https://openalex.org/W4297841817","https://openalex.org/W4372272479","https://openalex.org/W4385822352","https://openalex.org/W4385822353","https://openalex.org/W4391021780","https://openalex.org/W4400047235","https://openalex.org/W4404781824","https://openalex.org/W4412945230","https://openalex.org/W4415432729"],"related_works":[],"abstract_inverted_index":{"The":[0,70],"development":[1,104],"of":[2,75,96,105],"a":[3,8,28,32,93],"spoken":[4,10,16,35,58,67],"dialogue":[5,11,17,36,40,59,68,107,126],"system":[6],"requires":[7],"large-scale":[9,33],"corpus.":[12],"However,":[13],"existing":[14],"Japanese":[15,34],"corpora":[18],"are":[19],"limited":[20],"in":[21],"size.":[22],"In":[23],"this":[24],"study,":[25],"we":[26],"propose":[27],"method":[29],"for":[30,65,102,124],"constructing":[31],"dataset":[37,72,112],"by":[38],"collecting":[39],"videos":[41,47],"from":[42],"YouTube.":[43],"Since":[44],"YouTube":[45],"hosts":[46],"across":[48],"various":[49],"genres,":[50],"recording":[51],"environments,":[52],"and":[53],"speakers,":[54],"it":[55,90,100,118],"provides":[56],"diverse":[57],"data":[60],"that":[61],"can":[62],"be":[63,122],"utilized":[64],"developing":[66],"systems.":[69,108],"constructed":[71],"primarily":[73],"consists":[74],"twospeaker":[76],"dialogues":[77,83],"but":[78],"also":[79],"includes":[80,113],"many":[81,114],"multi-party":[82,106],"involving":[84],"five":[85],"or":[86],"more":[87],"participants.":[88],"Additionally,":[89],"contains":[91],"only":[92],"small":[94],"amount":[95],"non-dialogue":[97],"speech,":[98],"making":[99],"suitable":[101],"the":[103,111],"Furthermore,":[109],"since":[110],"relatively":[115],"long":[116],"dialogues,":[117],"is":[119],"expected":[120],"to":[121],"useful":[123],"long-duration":[125],"applications.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
