{"id":"https://openalex.org/W207735548","doi":"https://doi.org/10.21437/interspeech.2004-563","title":"Disambiguation in determining phonemes of sound-imitation words for environmental sound recognition","display_name":"Disambiguation in determining phonemes of sound-imitation words for environmental sound recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W207735548","doi":"https://doi.org/10.21437/interspeech.2004-563","mag":"207735548"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5075344540","display_name":"Yuya Hattori","orcid":"https://orcid.org/0000-0002-6927-980X"},"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":"Yuya Hattori","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/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"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/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":"Kazunori Komatani","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/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"]},{"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":"Tetsuya Ogata","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":2,"institutions_distinct_count":6,"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":0.2811,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51548309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1485","last_page":"1488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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":0.9955999851226807,"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/T12032","display_name":"Multisensory perception and integration","score":0.9905999898910522,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9757000207901001,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7603904008865356},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6865605115890503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6639777421951294},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6387443542480469},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5981026887893677},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5180435180664062},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.465142160654068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43068578839302063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32583409547805786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2973286509513855},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21138837933540344},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09936481714248657}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7603904008865356},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6865605115890503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639777421951294},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6387443542480469},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5981026887893677},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5180435180664062},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.465142160654068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43068578839302063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32583409547805786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2973286509513855},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21138837933540344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09936481714248657},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-563","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W110200507","https://openalex.org/W1567619397","https://openalex.org/W1992153276"],"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/W2353179089"],"abstract_inverted_index":{"Onomatopoeia,":[0],"or":[1,89,106],"sound-imitation":[2],"words":[3],"(SIWs)":[4],"are":[5],"important":[6],"in":[7,11,18],"informing":[8],"sound":[9,34,111],"events":[10],"human-computer":[12],"communication.":[13],"One":[14],"problem":[15,62,97],"is":[16,51,98,116],"listener-dependency":[17],"recognizing":[19],"environmental":[20,33,81],"sounds":[21],"by":[22,103],"means":[23],"of":[24,47,63,70,87,146],"SIWs,":[25],"that":[26,130],"is,":[27],"different":[28,37],"listener":[29],"hears":[30],"the":[31,41,45,76,95,122,136,143],"same":[32,42],"as":[35,75],"a":[36,68,110],"SIW":[38,132],"even":[39],"under":[40],"condition.":[43],"Therefore,":[44],"use":[46],"usual":[48],"Japanese":[49,91],"phonemes":[50],"not":[52],"adequate":[53],"to":[54,74,79,118],"express":[55],"SIWs.":[56],"To":[57],"cope":[58],"with":[59,126],"this":[60],"ambiguity":[61,96],"phoneme":[64],"determination,":[65],"we":[66],"designed":[67],"set":[69],"new":[71],"phonemes,":[72,92],"referred":[73],"basic":[77,84,137],"phoneme-groups,":[78],"represent":[80],"sounds.":[82],"The":[83,148],"phonemegroup":[85],"consists":[86],"one":[88,105],"more":[90,107],"and":[93,150,155],"thus":[94],"resolved":[99],"based":[100,134,141],"on":[101,135,142],"it":[102],"generating":[104],"SIWs":[108,120],"for":[109],"event.":[112],"An":[113],"HMM-based":[114],"scheme":[115],"adopted":[117],"recognize":[119],"using":[121],"phoneme-groups.":[123],"Listening":[124],"experiments":[125],"seven":[127],"subjects":[128],"showed":[129],"automatic":[131],"recognition":[133],"phoneme-groups":[138],"outperformed":[139],"ones":[140],"other":[144],"types":[145],"phonemes.":[147],"recall":[149],"precision":[151],"rate":[152],"were":[153],"56.4%":[154],"72.2%,":[156],"respectively.":[157]},"counts_by_year":[{"year":2019,"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"}
