{"id":"https://openalex.org/W179346709","doi":"https://doi.org/10.21437/eurospeech.2003-716","title":"Improvement of non-native speech recognition by effectively modeling frequently observed pronunciation habits","display_name":"Improvement of non-native speech recognition by effectively modeling frequently observed pronunciation habits","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W179346709","doi":"https://doi.org/10.21437/eurospeech.2003-716","mag":"179346709"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-716","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-716","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":"conference-paper","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/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012567655","display_name":"Koichi Osaki","orcid":"https://orcid.org/0000-0002-2051-9980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koichi Osaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2597","last_page":"2600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/pronunciation","display_name":"Pronunciation","score":0.862781286239624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8513121008872986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7279478907585144},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.7152764201164246},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6772228479385376},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5856001973152161},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5718875527381897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5480676889419556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4986460208892822},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4360750615596771},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42709264159202576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3485429286956787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12251684069633484}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.862781286239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513121008872986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7279478907585144},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.7152764201164246},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6772228479385376},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5856001973152161},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5718875527381897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5480676889419556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4986460208892822},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4360750615596771},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42709264159202576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3485429286956787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12251684069633484},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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.2003-716","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-716","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","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W153989523","https://openalex.org/W335030537","https://openalex.org/W2045070791","https://openalex.org/W2086705963","https://openalex.org/W2405879112"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W2140347529"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"two":[3,104],"techniques":[4],"are":[5,117,124],"proposed":[6,153],"to":[7,126],"enhance":[8],"the":[9,41,86,103,115,128,133,139,152],"nonnative":[10],"(Japanese":[11],"English)":[12],"speech":[13],"recognition":[14,122],"performance.":[15],"The":[16,89],"first":[17],"technique":[18,91],"effectively":[19],"integrates":[20],"orthographic":[21],"representation":[22],"of":[23,60,113,138,144,150],"a":[24,61,71,94,135],"phoneme":[25,62,111,121],"as":[26,81],"an":[27,82],"additional":[28,83],"context":[29,84],"in":[30,33,85],"state":[31,87],"clustering":[32],"training":[34],"tied-state":[35],"triphones.":[36],"Non-native":[37],"speakers":[38],"often":[39],"learned":[40],"target":[42],"language":[43],"not":[44],"through":[45,49],"their":[46,50,58],"ears":[47],"but":[48],"eyes":[51],"and":[52,73,79,130],"it":[53],"is":[54,76,141],"easily":[55],"assumed":[56],"that":[57],"pronunciation":[59],"may":[63],"depend":[64],"upon":[65,132],"its":[66,74],"grapheme.":[67],"Here,":[68,119],"correspondence":[69],"between":[70,102],"vowel":[72],"grapheme":[75],"automatically":[77],"extracted":[78],"used":[80],"clustering.":[88],"second":[90],"elaborately":[92],"couples":[93],"Japanese":[95],"English":[96],"acoustic":[97],"model":[98],"using":[99],"triphones,":[100],"mapping":[101],"models":[105,116],"should":[106],"be":[107],"carefully":[108],"trained":[109],"because":[110],"sets":[112],"both":[114,151],"different.":[118],"several":[120],"experiments":[123,146],"done":[125],"induce":[127],"mapping,":[129,134],"based":[131],"tentative":[136],"method":[137],"coupling":[140],"examined.":[142],"Results":[143],"LVCSR":[145],"show":[147],"high":[148],"validity":[149],"methods.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}