{"id":"https://openalex.org/W2796182971","doi":"https://doi.org/10.1109/devlrn.2017.8329801","title":"Unsupervised learning for spoken word production based on simultaneous word and phoneme discovery without transcribed data","display_name":"Unsupervised learning for spoken word production based on simultaneous word and phoneme discovery without transcribed data","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2796182971","doi":"https://doi.org/10.1109/devlrn.2017.8329801","mag":"2796182971"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2017.8329801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5074353113","display_name":"Yuusuke Miyuki","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuusuke Miyuki","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064096346","display_name":"Yoshinobu Hagiwara","orcid":"https://orcid.org/0009-0006-1208-3159"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinobu Hagiwara","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023160093","display_name":"Tadahiro Taniguchi","orcid":"https://orcid.org/0000-0002-5682-2076"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadahiro Taniguchi","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074353113"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65669652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"81","issue":null,"first_page":"156","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9911999702453613,"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":0.809358537197113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6994545459747314},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6317755579948425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6197149157524109},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5286886096000671},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.522623598575592},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5209971070289612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49677497148513794},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4543426036834717},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4402443468570709},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4294975996017456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809358537197113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6994545459747314},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6317755579948425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6197149157524109},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5286886096000671},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.522623598575592},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5209971070289612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49677497148513794},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4543426036834717},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4402443468570709},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4294975996017456},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2017.8329801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1567832587","https://openalex.org/W1778492285","https://openalex.org/W1922655562","https://openalex.org/W1935012542","https://openalex.org/W1942713348","https://openalex.org/W1979449467","https://openalex.org/W1980862600","https://openalex.org/W1983146955","https://openalex.org/W1987774416","https://openalex.org/W1995122024","https://openalex.org/W2005958977","https://openalex.org/W2011934537","https://openalex.org/W2020944885","https://openalex.org/W2022058071","https://openalex.org/W2055226328","https://openalex.org/W2111284386","https://openalex.org/W2115867364","https://openalex.org/W2124271233","https://openalex.org/W2129142580","https://openalex.org/W2132991226","https://openalex.org/W2140991203","https://openalex.org/W2142111485","https://openalex.org/W2147768505","https://openalex.org/W2158266063","https://openalex.org/W2184270665","https://openalex.org/W2193413348","https://openalex.org/W2220867547","https://openalex.org/W2256409625","https://openalex.org/W2335112305","https://openalex.org/W2346964103","https://openalex.org/W2581478358","https://openalex.org/W2598638573","https://openalex.org/W2795648103","https://openalex.org/W2949115596","https://openalex.org/W3100945159","https://openalex.org/W3102667484","https://openalex.org/W3104490327","https://openalex.org/W4234588466","https://openalex.org/W4309301076","https://openalex.org/W6634986005","https://openalex.org/W6635085004","https://openalex.org/W6640777149","https://openalex.org/W6686102742","https://openalex.org/W6824062597"],"related_works":["https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W4300049944","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W4366957107"],"abstract_inverted_index":{"A":[0],"computational":[1],"model":[2,30],"that":[3,102,119,152,214,230,239,261],"can":[4,124,234,240,262],"reproduce":[5],"the":[6,24,55,73,110,120,138,200,206,231,244,249],"process":[7],"of":[8,54],"language":[9],"acquisition,":[10],"including":[11],"word":[12,100],"discovery":[13],"and":[14,49,61,66,159,167,192,219,267],"generation,":[15],"by":[16,63,68,199,248],"human":[17,25,64,250],"children":[18],"is":[19,113,135,146],"crucially":[20],"important":[21],"in":[22,163,257],"understanding":[23],"developmental":[26],"process.":[27],"Such":[28],"a":[29,131,154,168,259],"should":[31],"not":[32,104],"depend":[33],"on":[34,137],"transcribed":[35,76,82,88,107],"data,":[36,77,108],"which":[37,145,177],"are":[38,202],"often":[39],"provided":[40,247],"manually":[41],"when":[42],"researchers":[43],"train":[44,205],"artificial":[45],"automatic":[46],"speech":[47,50,59,117,164,174],"recognition":[48,60],"synthesis":[51,175],"systems.":[52,186],"One":[53],"main":[56],"differences":[57],"between":[58],"production":[62,101],"infants":[65],"those":[67],"conventional":[69],"computer":[70],"systems":[71,266],"concerns":[72],"access":[74],"to":[75,156,182,204],"i.e.,":[78,109,189,195],"supervised":[79],"learning":[80,86,96,150],"with":[81],"data":[83],"or":[84],"unsupervised":[85,94,148],"without":[87],"data.":[89],"This":[90],"study":[91],"proposes":[92],"an":[93,147,220],"machine":[95,149],"method":[97,134,151,233],"for":[98],"spoken":[99,222,237],"does":[103],"use":[105],"any":[106],"entire":[111],"system":[112,121],"trained":[114],"purely":[115],"using":[116],"signals":[118,165],"(the":[122],"robot)":[123],"obtain":[125],"from":[126,270],"its":[127],"auditory":[128],"sensor,":[129],"e.g.,":[130],"microphone.":[132],"The":[133],"based":[136],"nonparametric":[139],"Bayesian":[140],"double":[141],"articulation":[142],"analyzer":[143],"(NPB-DAA),":[144],"enables":[153],"robot":[155,260],"identify":[157],"word-like":[158,196],"phoneme-like":[160,190],"linguistic":[161],"units":[162],"alone,":[166],"hidden":[169],"Markov":[170],"model-based":[171],"(HMM-based)":[172],"statistical":[173],"method,":[176],"has":[178],"been":[179],"widely":[180],"used":[181,203,215],"develop":[183],"text-to-speech":[184],"(TTS)":[185],"Latent":[187],"letters,":[188],"units,":[191,197],"latent":[193],"words,":[194],"discovered":[198],"NPB-DAA":[201],"HMM-based":[207],"TTS":[208],"system.":[209],"We":[210],"present":[211],"two":[212],"experiments":[213],"Japanese":[216],"vowel":[217],"sequences":[218],"English":[221],"digit":[223],"corpus,":[224],"respectively.":[225],"Both":[226],"experimental":[227],"results":[228],"showed":[229],"proposed":[232],"produce":[235],"many":[236],"words":[238,246],"be":[241],"recognized":[242],"as":[243],"original":[245],"speakers.":[251],"Furthermore,":[252],"we":[253],"discuss":[254],"future":[255],"challenges":[256],"creating":[258],"autonomously":[263],"learn":[264],"phoneme":[265],"vocabulary":[268],"only":[269],"sensor-motor":[271],"information.":[272]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}