{"id":"https://openalex.org/W110200507","doi":"https://doi.org/10.21437/eurospeech.2003-796","title":"Automatic transformation of environmental sounds into sound-imitation words based on Japanese syllable structure","display_name":"Automatic transformation of environmental sounds into sound-imitation words based on Japanese syllable structure","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W110200507","doi":"https://doi.org/10.21437/eurospeech.2003-796","mag":"110200507"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-796","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5113636387","display_name":"Kazushi Ishihara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"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":"Kazushi Ishihara","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019830976","display_name":"Yasushi Tsubota","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"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasushi Tsubota","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"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/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113636387"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"],"apc_list":null,"apc_paid":null,"fwci":2.3425,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88853687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3185","last_page":"3188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9083999991416931,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9083999991416931,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9046000242233276,"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/imitation","display_name":"Imitation","score":0.7734383344650269},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7481931447982788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6478438973426819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.602251410484314},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5484304428100586},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4804663062095642},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46234312653541565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4331624507904053},{"id":"https://openalex.org/keywords/natural-sounds","display_name":"Natural sounds","score":0.42406001687049866},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.41431140899658203},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3495689630508423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34773826599121094},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18277215957641602},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12553763389587402},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.09219801425933838}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7734383344650269},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7481931447982788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478438973426819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.602251410484314},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5484304428100586},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4804663062095642},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46234312653541565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4331624507904053},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.42406001687049866},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.41431140899658203},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3495689630508423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34773826599121094},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18277215957641602},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12553763389587402},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09219801425933838},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-796","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W1992153276","https://openalex.org/W2319849464"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W1531601525","https://openalex.org/W2031813887","https://openalex.org/W3008534511","https://openalex.org/W2355100508","https://openalex.org/W2169277706"],"abstract_inverted_index":{"Abstract":[0],"Sound-imitation":[1],"words":[2,34,74],",":[3,9],"a":[4,42],"sound-related":[5],"subset":[6],"of":[7,17,25,32,50,61,93,95,112],"ono-matopoeia":[8],"are":[10],"important":[11],"for":[12],"computer-human":[13],"interaction":[14,121],"andautomatic":[15],"tagging":[16],"sound":[18],"archives.":[19],"The":[20,109],"main":[21],"problemof":[22],"automatic":[23,113],"recognition":[24,115],"sound-imitation":[26,73],"word":[27],"is":[28,35,75],"that":[29,58],"theliteral":[30],"representation":[31],"such":[33,51,142],"dependent":[36],"on":[37,85],"listen-ers":[38],"and":[39,53,78,90,102,122],"in\ufb02uenced":[40,79],"by":[41,80],"particular":[43],"cultural":[44],"history.":[45],"Basedon":[46],"our":[47],"preliminary":[48],"experiments":[49],"dependency":[52],"thesonority":[54],"theory,":[55],"we":[56],"discovered":[57],"the":[59,86],"process":[60,89],"transform-ing":[62],"environmental":[63,140],"sounds":[64,141],"into":[65,72],"syllable-structure":[66],"expressions":[67,71],"ismostly":[68],"listener-independent":[69],"whilethatoftransformingsyllable-structure":[70],"mostly":[76],"listener-dependent":[77],"culture.":[81],"This":[82],"paper":[83],"fo-cuses":[84],"former":[87],"lister-independent":[88],"presents":[91],"thethree-stagearchitecture":[92],"automatictransformation":[94],"environ-mentalsounds":[96],"tosound-imitationwords;":[97],"segmenting":[98],"soundsig-nalstosyllables,":[99],"identifying":[100],"syllablestructureasmora,":[101],"rec-ognizing":[103],"mora":[104],"as":[105,143],"phonemes.":[106],"1.":[107],"Introduction":[108],"recent":[110],"development":[111],"speech":[114,124],"sys-tems":[116],"(ASR)":[117],"has":[118],"enhanced":[119],"human-computer":[120],"en-abled":[123],"input":[125],"over":[126],"normal":[127],"or":[128,148],"cellular":[129],"phones.":[130],"CurrentASR\u2019s,":[131],"however,":[132],"fail":[133],"in":[134,138],"recognizing":[135],"non-speech":[136],"sounds,":[137],"par-ticular":[139],"animal":[144],"voices,":[145],"instrumen-tal,":[146],"natural,":[147],"machine":[149],"sounds.":[150],"Japanese":[151],"speaking":[152],"people":[153],"of-ten":[154],"use":[155]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
