{"id":"https://openalex.org/W4205876710","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660413","title":"Self-Supervised Spoken Question Understanding and Speaking with Automatic Vocabulary Learning","display_name":"Self-Supervised Spoken Question Understanding and Speaking with Automatic Vocabulary Learning","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4205876710","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660413"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066819114","display_name":"Keisuke Toyoda","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Toyoda","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061390903","display_name":"Yusuke Kimura","orcid":"https://orcid.org/0000-0002-7353-5765"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kimura","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700674","display_name":"Mingxin Zhang","orcid":"https://orcid.org/0000-0002-8214-2728"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mingxin Zhang","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005288345","display_name":"Kent Hino","orcid":"https://orcid.org/0009-0003-3060-581X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kent Hino","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059614616","display_name":"Kosuke Mori","orcid":"https://orcid.org/0000-0002-2992-056X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kosuke Mori","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"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":"1","issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957000017166138,"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/T12031","display_name":"Speech and dialogue systems","score":0.9957000017166138,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9746000170707703,"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/computer-science","display_name":"Computer science","score":0.7633170485496521},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6753718256950378},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6711271405220032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5688373446464539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49729159474372864},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.47706878185272217},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.44627341628074646},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.4214283525943756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633170485496521},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6753718256950378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6711271405220032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688373446464539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49729159474372864},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.47706878185272217},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44627341628074646},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.4214283525943756},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1771552368","https://openalex.org/W2107019937","https://openalex.org/W2127218421","https://openalex.org/W2194775991","https://openalex.org/W2591896182","https://openalex.org/W2962780374","https://openalex.org/W2964169922","https://openalex.org/W2990408345","https://openalex.org/W2995680346","https://openalex.org/W3016208931","https://openalex.org/W3096020106","https://openalex.org/W3096215352","https://openalex.org/W4251072654","https://openalex.org/W4295312788","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6678914141","https://openalex.org/W6766978945","https://openalex.org/W6770596778","https://openalex.org/W6770805772"],"related_works":["https://openalex.org/W3019875293","https://openalex.org/W2351746492","https://openalex.org/W2367621846","https://openalex.org/W2394096350","https://openalex.org/W2091742426","https://openalex.org/W2365662948","https://openalex.org/W1988910916","https://openalex.org/W2380430606","https://openalex.org/W4360597343","https://openalex.org/W4287151890"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"acquisition":[2,42],"involves":[3],"automatically":[4],"developing":[5],"symbolic":[6],"word":[7,40],"concepts":[8],"grounding":[9],"their":[10],"meaning":[11],"to":[12,57,69,85,88,146],"the":[13,16,33,39,54,62,86,99,111,119,123,136,142,147],"world,":[14,63],"recognizing":[15],"words":[17],"in":[18,105],"spoken":[19],"utterances,":[20],"and":[21,48,50,109],"pronouncing":[22,65],"them.":[23],"Previous":[24],"research":[25],"only":[26,64],"partly":[27],"covered":[28],"these":[29],"aspects.":[30],"One":[31],"of":[32,45,132],"most":[34],"comprehensive":[35],"agent":[36,55,87,100,120],"systems":[37],"supported":[38],"concept":[41],"from":[43],"pairs":[44],"raw":[46],"speech":[47],"image":[49],"utterance":[51,108],"pronunciation.":[52],"However,":[53],"listened":[56],"nothing":[58],"when":[59],"interacting":[60],"with":[61],"a":[66,71,83,90,96,103,106],"food":[67,137],"name":[68],"choose":[70],"favorite":[72],"one":[73,144],"among":[74],"two":[75],"shown":[76],"images.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,94],"add":[82],"function":[84],"recognize":[89,102],"verbal":[91],"question.":[92,148],"Namely,":[93],"design":[95],"task":[97],"where":[98],"must":[101],"question":[104],"sound":[107],"understand":[110],"logical":[112],"\u201cnot\u201d":[113],"concept.":[114],"Experimental":[115],"results":[116],"show":[117],"that":[118],"successfully":[121],"learns":[122],"task.":[124],"It":[125],"appropriately":[126],"behaves":[127],"even":[128],"for":[129],"unseen":[130],"combinations":[131],"images,":[133],"correctly":[134],"answering":[135],"names":[138],"it":[139],"wants":[140],"or":[141],"opposite":[143],"according":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}