{"id":"https://openalex.org/W4372348373","doi":"https://doi.org/10.1109/icassp49357.2023.10096250","title":"Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder","display_name":"Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348373","doi":"https://doi.org/10.1109/icassp49357.2023.10096250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096250","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Ryota Komatsu","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology","institution_ids":["https://openalex.org/I90023481"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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":0.8310549259185791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6268354058265686},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6040643453598022},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5693955421447754},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5622591376304626},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5589990019798279},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180899500846863},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.47276192903518677},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4576212167739868},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41180622577667236},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.38379693031311035},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11046227812767029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310549259185791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6268354058265686},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6040643453598022},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5693955421447754},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5622591376304626},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5589990019798279},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180899500846863},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.47276192903518677},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4576212167739868},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41180622577667236},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38379693031311035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11046227812767029},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/icassp49357.2023.10096250","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"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"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W98451546","https://openalex.org/W1959608418","https://openalex.org/W2019055305","https://openalex.org/W2020944885","https://openalex.org/W2038594453","https://openalex.org/W2108598243","https://openalex.org/W2112366626","https://openalex.org/W2134670479","https://openalex.org/W2142927041","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2407753819","https://openalex.org/W2483390977","https://openalex.org/W2519091744","https://openalex.org/W2556930864","https://openalex.org/W2766365052","https://openalex.org/W2810346659","https://openalex.org/W2963864421","https://openalex.org/W2964169922","https://openalex.org/W2964243274","https://openalex.org/W2978613765","https://openalex.org/W2995680346","https://openalex.org/W2998557583","https://openalex.org/W3016208931","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3094502228","https://openalex.org/W3096020106","https://openalex.org/W3123097577","https://openalex.org/W3159481202","https://openalex.org/W3174311593","https://openalex.org/W4253682481","https://openalex.org/W4285225028","https://openalex.org/W4385245566","https://openalex.org/W6640963894","https://openalex.org/W6679792166","https://openalex.org/W6684921986","https://openalex.org/W6729977899","https://openalex.org/W6735305794","https://openalex.org/W6739901393","https://openalex.org/W6753101812","https://openalex.org/W6768238010","https://openalex.org/W6770596778","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2911655849","https://openalex.org/W4286432911"],"abstract_inverted_index":{"Studies":[0],"on":[1,19],"spoken":[2],"language":[3,13,141],"acquisition":[4],"agents":[5,24],"aim":[6],"to":[7,16,33,48,95,104],"understand":[8,49],"the":[9,50,53,56,101,112,127,150],"mechanism":[10,94],"of":[11,52,133,143],"human":[12],"learning":[14,29,47,98,158],"and":[15,43,135,163],"realize":[17],"it":[18,116],"computers.":[20],"Existing":[21],"open":[22],"vocabulary":[23],"first":[25],"perform":[26],"unsupervised":[27,157],"word":[28,36],"from":[30],"speech":[31,134,162],"signals":[32],"construct":[34],"a":[35,39,84,92,139],"dictionary":[37,57],"as":[38,126],"discrete":[40],"action":[41,86,128],"space":[42],"then":[44],"conduct":[45],"reinforcement":[46],"use":[51],"words":[54],"in":[55,107],"through":[58],"interaction":[59],"with":[60,117,122],"dialogue":[61],"partners.":[62],"A":[63],"limitation":[64],"is":[65],"that":[66,78,149],"they":[67],"have":[68],"difficulty":[69],"pronouncing":[70],"multi-word":[71,80,153],"utterances.":[72],"This":[73],"study":[74],"proposes":[75],"an":[76],"agent":[77,90,114,131,151],"generates":[79],"waveform":[81],"utterances":[82,154],"using":[83,160],"continuous":[85],"space.":[87,129,145],"The":[88,130],"conventional":[89],"uses":[91],"vision-focusing":[93],"accelerate":[96],"dialogue-based":[97],"by":[99,156],"guiding":[100],"agent\u2019s":[102],"attention":[103],"those":[105],"concepts":[106],"its":[108],"eyesight.":[109],"In":[110],"contrast,":[111],"proposed":[113],"replaces":[115],"residual":[118],"sentence":[119],"embedding":[120],"combined":[121],"vision":[123],"features":[124],"used":[125],"consists":[132],"image":[136,164],"input":[137],"front-ends,":[138],"transformer":[140],"model":[142],"pseudo-action":[144],"Experimental":[146],"results":[147],"show":[148],"learns":[152],"assisted":[155],"algorithms":[159],"unlabeled":[161],"data":[165],"sets.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}