{"id":"https://openalex.org/W2105882611","doi":"https://doi.org/10.1109/iros.2008.4651060","title":"Segmenting acoustic signal with articulatory movement using Recurrent Neural Network for phoneme acquisition","display_name":"Segmenting acoustic signal with articulatory movement using Recurrent Neural Network for phoneme acquisition","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2105882611","doi":"https://doi.org/10.1109/iros.2008.4651060","mag":"2105882611"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2008.4651060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2008.4651060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5009009276","display_name":"Hisashi Kanda","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"H. Kanda","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan","Grad. Sch. of Inf., Kyoto-Univ., Kyoto"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Kyoto-Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Ogata","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan","Grad. Sch. of Inf., Kyoto-Univ., Kyoto"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Kyoto-Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Komatani","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan","Grad. Sch. of Inf., Kyoto-Univ., Kyoto"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Kyoto-Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H.G. Okuno","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan","Grad. Sch. of Inf., Kyoto-Univ., Kyoto"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Grad. Sch. of Inf., Kyoto-Univ., Kyoto","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009009276"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":2.8603,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91435076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"j61 a","issue":null,"first_page":"1712","last_page":"1717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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":0.9987000226974487,"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/speech-recognition","display_name":"Speech recognition","score":0.7741929888725281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442944049835205},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6513634920120239},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.599653422832489},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5412099361419678},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5380631685256958},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5049923062324524},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4912869334220886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.482302188873291},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4820452630519867},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45157355070114136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3798235356807709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32448139786720276},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20029985904693604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10005494952201843},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08847695589065552}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7741929888725281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442944049835205},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6513634920120239},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.599653422832489},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5412099361419678},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5380631685256958},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5049923062324524},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4912869334220886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.482302188873291},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4820452630519867},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45157355070114136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3798235356807709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32448139786720276},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20029985904693604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10005494952201843},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08847695589065552},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2008.4651060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2008.4651060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W123135133","https://openalex.org/W1640915152","https://openalex.org/W1926768285","https://openalex.org/W1959983357","https://openalex.org/W1966072864","https://openalex.org/W2021743383","https://openalex.org/W2069501481","https://openalex.org/W2130876672","https://openalex.org/W2142344747","https://openalex.org/W2145097496","https://openalex.org/W2147677349","https://openalex.org/W2150423550","https://openalex.org/W2163180231","https://openalex.org/W2319571881","https://openalex.org/W2766736793","https://openalex.org/W3094114204","https://openalex.org/W6641231757","https://openalex.org/W6681576234"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2079194684"],"abstract_inverted_index":{"This":[0,133,197],"paper":[1],"proposes":[2],"a":[3,94,141,173],"computational":[4],"model":[5,201],"for":[6,36],"phoneme":[7,19,31,206],"acquisition":[8,32],"by":[9,78,107,125,157,171],"infants.":[10],"Human":[11],"infants":[12],"perceive":[13,62],"speech":[14,40,63],"sounds":[15,105],"not":[16],"as":[17,22,54,163],"discrete":[18],"sequences":[20],"but":[21],"continuous":[23,39,86,195],"acoustic":[24,112],"signals.":[25],"One":[26],"of":[27,85,148,165,205],"critical":[28],"problems":[29],"in":[30,82,140,193],"is":[33,49,76],"the":[34,55,71,83,99,108,119,136,145,149,153,158,179,190,203],"design":[35],"segmenting":[37,120],"these":[38],"sounds.":[41,196],"The":[42],"key":[43],"idea":[44],"to":[45,61,67,73,122],"solve":[46],"this":[47],"problem":[48],"that":[50,185,199],"articulatory":[51,89,102,115],"mechanisms":[52],"such":[53],"vocal":[56,95,175],"tract":[57,176],"help":[58],"human":[59],"beings":[60],"sound":[64,87],"units":[65],"corresponding":[66],"phonemes.":[68,166],"That":[69],"is,":[70],"ability":[72],"distinguish":[74],"phonemes":[75,192],"learned":[77],"recognizing":[79],"unstable":[80],"points":[81],"dynamics":[84],"with":[88,114,129],"movement.":[90],"We":[91],"have":[92],"developed":[93],"imitation":[96],"system":[97,124,168,187],"embodying":[98],"relationship":[100],"between":[101],"movements":[103],"and":[104,152],"produced":[106],"movements.":[109],"To":[110],"segment":[111],"signal":[113],"movement,":[116],"we":[117],"apply":[118],"method":[121,134,159],"our":[123,186,200],"recurrent":[126],"neural":[127],"network":[128],"parametric":[130],"bias":[131],"(RNNPB).":[132],"determines":[135],"multiple":[137],"segmentation":[138],"boundaries":[139],"temporal":[142],"sequence":[143],"using":[144,172],"prediction":[146],"error":[147],"RNNPB":[150],"model,":[151,177],"PB":[154],"values":[155],"obtained":[156],"can":[160,188],"be":[161],"encoded":[162],"kind":[164],"Our":[167],"was":[169],"implemented":[170],"physical":[174],"called":[178],"Maeda":[180],"model.":[181],"Experimental":[182],"results":[183],"demonstrated":[184],"self-organize":[189],"same":[191],"different":[194],"suggests":[198],"reflects":[202],"process":[204],"acquisition.":[207]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}