{"id":"https://openalex.org/W4401908170","doi":"https://doi.org/10.1109/icdl61372.2024.10644607","title":"Unsupervised Acquisition of Phonemes, Words, and Grammar from Continuous Speech Signals","display_name":"Unsupervised Acquisition of Phonemes, Words, and Grammar from Continuous Speech Signals","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4401908170","doi":"https://doi.org/10.1109/icdl61372.2024.10644607"},"language":"en","primary_location":{"id":"doi:10.1109/icdl61372.2024.10644607","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icdl61372.2024.10644607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Development and Learning (ICDL)","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/A5112298024","display_name":"Shoma Ochiai","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shoma Ochiai","raw_affiliation_strings":["The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054151238","display_name":"Masatoshi Nagano","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Nagano","raw_affiliation_strings":["The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102873917","display_name":"Tomoaki Nakamura","orcid":"https://orcid.org/0000-0002-6468-5745"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki Nakamura","raw_affiliation_strings":["The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Department of Mechanical and Intelligence Systems Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112298024"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11768139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7527916431427002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6368442177772522},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5954314470291138},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5570884346961975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4818342924118042},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3012714982032776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527916431427002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6368442177772522},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5954314470291138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5570884346961975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4818342924118042},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3012714982032776},{"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/icdl61372.2024.10644607","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icdl61372.2024.10644607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W142534928","https://openalex.org/W1980862600","https://openalex.org/W2020944885","https://openalex.org/W2037752261","https://openalex.org/W2038056950","https://openalex.org/W2042433305","https://openalex.org/W2064909871","https://openalex.org/W2076493153","https://openalex.org/W2078771686","https://openalex.org/W2090361527","https://openalex.org/W2101509422","https://openalex.org/W2105438133","https://openalex.org/W2121715942","https://openalex.org/W2147768505","https://openalex.org/W2165627680","https://openalex.org/W2335112305","https://openalex.org/W2537965973","https://openalex.org/W2781453719","https://openalex.org/W2890197052","https://openalex.org/W2910193102","https://openalex.org/W2963475757","https://openalex.org/W2963640382","https://openalex.org/W2980731151","https://openalex.org/W2981952374","https://openalex.org/W3098767311","https://openalex.org/W4230973462","https://openalex.org/W4235169531","https://openalex.org/W4386766515"],"related_works":["https://openalex.org/W2063575861","https://openalex.org/W3188962172","https://openalex.org/W2130654837","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Humans":[0],"can":[1,67,132],"acquire":[2],"language":[3,48],"by":[4,77],"segmenting":[5],"continuous":[6,74,134],"speech":[7,39,75,135],"signals":[8,40,76],"with":[9,46],"a":[10,60],"double":[11,35],"articulation":[12,36],"structure":[13,37],"into":[14,136],"phonemes":[15,109,118,137],"and":[16,24,71,86,103,110,119,138],"words":[17,30,139,160],"without":[18],"explicit":[19],"boundary":[20],"points":[21],"or":[22],"labels,":[23],"learn":[25,68],"the":[26,34,80,92,95,104,108,114,126,153,157,162],"transition":[27],"rules":[28],"of":[29,38,53,97,117,156,159],"as":[31],"grammar.":[32],"Learning":[33],"is":[41],"crucial":[42],"for":[43],"realizing":[44],"robots":[45],"similar":[47],"learning":[49,116,150],"abilities":[50],"to":[51],"those":[52],"humans.":[54],"In":[55,91],"this":[56],"study,":[57],"we":[58,146],"propose":[59],"novel":[61],"probabilistic":[62],"generative":[63],"model":[64,85,89],"(PGM)":[65],"that":[66,125,148],"phonemes,":[69],"words,":[70,111],"grammar":[72,130,149],"from":[73],"hierarchically":[78],"connecting":[79],"Gaussian":[81],"process":[82],"hidden":[83,87],"semi-Markov":[84,88],"(HSMM).":[90],"proposed":[93,127],"method,":[94],"parameters":[96],"each":[98],"PGM":[99],"are":[100],"updated":[101],"mutually":[102],"grammatical":[105],"structures":[106],"affect":[107],"thereby":[112],"enabling":[113],"accurate":[115,154],"words.":[120],"The":[121],"experimental":[122],"results":[123],"reveal":[124],"approach,":[128],"including":[129],"learning,":[131],"segment":[133],"more":[140],"accurately":[141],"than":[142],"conventional":[143],"methods.":[144],"Furthermore,":[145],"found":[147],"significantly":[151],"affected":[152],"estimation":[155],"number":[158],"in":[161],"sentence.":[163]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}