{"id":"https://openalex.org/W4285225028","doi":"https://doi.org/10.1109/jstsp.2022.3189279","title":"Automatic Spoken Language Acquisition Based on Observation and Dialogue","display_name":"Automatic Spoken Language Acquisition Based on Observation and Dialogue","publication_year":2022,"publication_date":"2022-07-07","ids":{"openalex":"https://openalex.org/W4285225028","doi":"https://doi.org/10.1109/jstsp.2022.3189279"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3189279","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3189279","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09817627.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09817627.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036072183","display_name":"Ryota Komatsu","orcid":"https://orcid.org/0000-0002-6139-0642"},"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":true,"raw_author_name":"Ryota Komatsu","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006287448","display_name":"Shengzhou Gao","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":"Shengzhou Gao","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027365025","display_name":"Wenxin Hou","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":"Wenxin Hou","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, 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, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"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":"Tomohiro Tanaka","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, 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, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, 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, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082871023","display_name":"Yu Iwamoto","orcid":"https://orcid.org/0000-0003-4388-9017"},"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":"Yu Iwamoto","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, 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, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Koganei, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Koganei, Tokyo, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","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":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Meguro, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5036072183"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.694,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74937376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"6","first_page":"1480","last_page":"1492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.9991999864578247,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9914000034332275,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9857000112533569,"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":0.7277995347976685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6127842664718628},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5529695153236389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5226873159408569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40132206678390503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277995347976685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6127842664718628},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5529695153236389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5226873159408569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40132206678390503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3189279","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3189279","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09817627.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2022.3189279","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3189279","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09817627.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5506463476","display_name":null,"funder_award_id":"JP22K1","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5897303658","display_name":"Spoken Language Acquisition Agent with Fluent Intonation","funder_award_id":"22K12069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6717573168","display_name":"\u300c\u30e2\u30f3\u30b9\u30fc\u30f3\u6587\u66f8\u300d\u306b\u3088\u308b\u30dd\u30eb\u30c8\u30ac\u30eb\u306e\u5bfe\u65e5\u8cbf\u6613\u306e\u7814\u7a76","funder_award_id":"12069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320331739","display_name":"Toray Science Foundation","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285225028.pdf","grobid_xml":"https://content.openalex.org/works/W4285225028.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W98451546","https://openalex.org/W1655830068","https://openalex.org/W1976144191","https://openalex.org/W2005581799","https://openalex.org/W2013035813","https://openalex.org/W2018381469","https://openalex.org/W2020944885","https://openalex.org/W2112366626","https://openalex.org/W2122410182","https://openalex.org/W2142927041","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2170469987","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2407753819","https://openalex.org/W2483390977","https://openalex.org/W2546571074","https://openalex.org/W2760103357","https://openalex.org/W2766365052","https://openalex.org/W2774977638","https://openalex.org/W2797583228","https://openalex.org/W2964169922","https://openalex.org/W2975414524","https://openalex.org/W2980731151","https://openalex.org/W3015338123","https://openalex.org/W3016208931","https://openalex.org/W3096020106","https://openalex.org/W3098767311","https://openalex.org/W3139377883","https://openalex.org/W3144035034","https://openalex.org/W3162075194","https://openalex.org/W3198769980","https://openalex.org/W3198772184","https://openalex.org/W3216772467","https://openalex.org/W4205876710","https://openalex.org/W4210287297","https://openalex.org/W4220814065","https://openalex.org/W4237938692","https://openalex.org/W4253682481","https://openalex.org/W6638318767","https://openalex.org/W6682849425","https://openalex.org/W6729977899","https://openalex.org/W6739271392","https://openalex.org/W6750665317","https://openalex.org/W6751433836","https://openalex.org/W6765775151","https://openalex.org/W6767111847","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6780559895","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6792155000","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Human":[0],"babies":[1],"are":[2,98],"born":[3],"without":[4,18],"knowledge":[5],"of":[6,24,43,93,179,185],"any":[7],"specific":[8],"language.":[9],"They":[10],"acquire":[11,144],"language":[12,30,82,87,146,186],"directly":[13],"from":[14,147],"observation":[15],"and":[16,55,72,117,129,176],"dialogue":[17,77],"being":[19],"limited":[20],"by":[21,149,156],"the":[22,35,94,99,131,135,177],"availability":[23],"labeled":[25],"data.":[26],"We":[27,166],"propose":[28],"spoken":[29,76,145],"acquisition":[31],"agents":[32,97,142,171],"that":[33,169],"simulate":[34],"process.":[36],"Such":[37],"an":[38,111,152],"ability":[39,88],"requires":[40],"multiple":[41],"types":[42,67],"learning,":[44],"including":[45],"1)":[46],"word":[47],"discovery,":[48],"2)":[49],"symbol":[50],"grounding,":[51],"3)":[52],"message":[53],"generation,":[54],"4)":[56],"pronunciation":[57],"generation.":[58],"Several":[59],"studies":[60],"have":[61],"targeted":[62],"one":[63],"or":[64],"combined":[65],"learning":[66,83,119,132,164],"to":[68,74,101,109,113,120,154],"elucidate":[69],"human":[70],"intelligence":[71],"aimed":[73],"equip":[75],"systems":[78],"with":[79,151],"human-like":[80],"flexible":[81],"ability.":[84],"However,":[85],"their":[86],"was":[89],"partially":[90],"lacking":[91],"some":[92],"components.":[95],"Our":[96,105,158],"first":[100],"integrate":[102,114],"them":[103],"all.":[104],"key":[106],"concept":[107,178],"is":[108],"design":[110],"architecture":[112],"unsupervised,":[115],"self-supervised,":[116],"reinforcement":[118],"utilize":[121],"clues":[122],"naturally":[123],"existing":[124],"in":[125],"raw":[126],"sensory":[127],"signals":[128],"drive":[130],"based":[133],"on":[134],"agent\u2019s":[136],"intrinsic":[137],"motivation.":[138],"Experimental":[139],"results":[140],"show":[141],"successfully":[143],"scratch":[148],"interacting":[150],"environment":[153],"act":[155],"speaking.":[157],"proposed":[159],"focusing":[160],"mechanism":[161],"significantly":[162],"improves":[163],"efficiency.":[165],"also":[167],"demonstrate":[168],"our":[170],"can":[172],"learn":[173],"neural":[174],"vocoder":[175],"logical":[180],"negation":[181],"as":[182],"a":[183],"part":[184],"acquisition.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}