{"id":"https://openalex.org/W2042281066","doi":"https://doi.org/10.1109/asru.2009.5373299","title":"MLLR/MAP adaptation using pronunciation variation for non-native speech recognition","display_name":"MLLR/MAP adaptation using pronunciation variation for non-native speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2042281066","doi":"https://doi.org/10.1109/asru.2009.5373299","mag":"2042281066"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5075854814","display_name":"Yoo Rhee Oh","orcid":"https://orcid.org/0000-0002-1557-0538"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoo Rhee Oh","raw_affiliation_strings":["Department of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, South Korea","Dept. of Information and Communications, Gwangju Institute of Science and Technology (GIST), 1 Oryong-dong, Buk-gu, 500-712, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, South Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"Dept. of Information and Communications, Gwangju Institute of Science and Technology (GIST), 1 Oryong-dong, Buk-gu, 500-712, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["Department of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, South Korea","Dept. of Information and Communications, Gwangju Institute of Science and Technology (GIST), 1 Oryong-dong, Buk-gu, 500-712, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communications, Gwangju Institute of Science and Technology, Gwangju, South Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"Dept. of Information and Communications, Gwangju Institute of Science and Technology (GIST), 1 Oryong-dong, Buk-gu, 500-712, Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075854814"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":2.1809,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88928436,"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":"216","last_page":"221"},"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/T10860","display_name":"Speech and Audio Processing","score":0.991100013256073,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9753999710083008,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.9251667261123657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.740702748298645},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006192207336426},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6336445212364197},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6011868119239807},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5871293544769287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.554607093334198},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5465455055236816},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.5372189879417419},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45194554328918457},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4450249671936035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4011165499687195},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2651350498199463},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15716490149497986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13731777667999268},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13341346383094788},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07911080121994019}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9251667261123657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740702748298645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006192207336426},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6336445212364197},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6011868119239807},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5871293544769287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554607093334198},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5465455055236816},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5372189879417419},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45194554328918457},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4450249671936035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4011165499687195},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2651350498199463},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15716490149497986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13731777667999268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13341346383094788},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07911080121994019},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"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/asru.2009.5373299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W56231661","https://openalex.org/W167428729","https://openalex.org/W174505309","https://openalex.org/W252927377","https://openalex.org/W1497396626","https://openalex.org/W1544284505","https://openalex.org/W1764939238","https://openalex.org/W1992155534","https://openalex.org/W2024490156","https://openalex.org/W2045070791","https://openalex.org/W2069508439","https://openalex.org/W2125055259","https://openalex.org/W2134483445","https://openalex.org/W2150248180","https://openalex.org/W2158069733","https://openalex.org/W2164098806","https://openalex.org/W2165504593","https://openalex.org/W2168911071","https://openalex.org/W6602293665","https://openalex.org/W6606836005","https://openalex.org/W6609584513","https://openalex.org/W6629756642","https://openalex.org/W6632774006","https://openalex.org/W6668123327","https://openalex.org/W6682221659","https://openalex.org/W6684732307"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W31220157","https://openalex.org/W2288557197","https://openalex.org/W4233024177","https://openalex.org/W2101914902"],"abstract_inverted_index":{"In":[0,118],"this":[1,33],"paper,":[2],"we":[3,35,46,87],"propose":[4],"an":[5,41,167],"acoustic":[6,103,126,133],"model":[7],"adaptation":[8,24,173,191],"method":[9,174],"based":[10],"on":[11],"a":[12,19,21,188],"maximum":[13,20],"likelihood":[14],"linear":[15],"regression":[16,51,56,76,84,99,116],"(MLLR)":[17],"and":[18,61,78],"posteriori":[22],"(MAP)":[23],"using":[25,40,96,112],"pronunciation":[26,38,67,82,108,114,146],"variations":[27,39,109,147],"for":[28,58,66,160],"non-native":[29,94,140,149,155],"speech":[30,95,157,165],"recognition.":[31],"To":[32],"end,":[34],"first":[36],"obtain":[37],"indirect":[42],"data-driven":[43],"approach.":[44],"Next,":[45,86],"generate":[47],"two":[48,91],"sets":[49,123],"of":[50,55,64,124,139,148],"classes:":[52],"one":[53],"composed":[54],"classes":[57,65,77],"all":[59],"pronunciations":[60],"the":[62,79,90,97,102,107,113,119,131,137,145,171,178],"other":[63],"variations.":[68],"The":[69],"former":[70],"are":[71,110,128],"referred":[72],"to":[73,93,187],"as":[74,81,142,144],"overall":[75,98],"latter":[80],"variation":[83,115],"classes.":[85,117],"sequentially":[88],"apply":[89],"adaptations":[92],"classes,":[100],"while":[101],"models":[104,127,134],"associated":[105],"with":[106],"adapted":[111,125],"final":[120],"step,":[121],"both":[122],"merged.":[129],"Thus,":[130],"resultant":[132],"can":[135,175],"cover":[136],"characteristics":[138],"speakers":[141],"well":[143],"speech.":[150],"It":[151],"is":[152],"shown":[153],"from":[154],"automatic":[156],"recognition":[158],"experiments":[159],"Korean":[161],"spoken":[162],"English":[163],"continuous":[164],"that":[166],"ASR":[168],"system":[169],"employing":[170],"proposed":[172],"relatively":[176],"reduce":[177],"average":[179],"word":[180],"error":[181],"rate":[182],"by":[183],"9.43%":[184],"when":[185],"compared":[186],"traditional":[189],"MLLR/MAP":[190],"method.":[192]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}