{"id":"https://openalex.org/W2408444966","doi":"https://doi.org/10.21437/slate.2009-35","title":"Improved structure-based automatic estimation of pronunciation proficiency","display_name":"Improved structure-based automatic estimation of pronunciation proficiency","publication_year":2009,"publication_date":"2009-09-03","ids":{"openalex":"https://openalex.org/W2408444966","doi":"https://doi.org/10.21437/slate.2009-35","mag":"2408444966"},"language":"en","primary_location":{"id":"doi:10.21437/slate.2009-35","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-35","pdf_url":"https://www.isca-archive.org/slate_2009/suzuki09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/slate_2009/suzuki09_slate.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112574077","display_name":"Dean Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dean Luo","raw_affiliation_strings":["The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.453,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77722136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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":0.9915000200271606,"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":0.8433144092559814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400978803634644},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6584089398384094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5997800230979919},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5857494473457336},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5055773258209229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47193047404289246},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4534949064254761},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.436952143907547},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.43144452571868896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42554765939712524},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4240737557411194},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.21145150065422058},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19575229287147522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15464523434638977}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8433144092559814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400978803634644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6584089398384094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5997800230979919},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5857494473457336},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5055773258209229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47193047404289246},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4534949064254761},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.436952143907547},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.43144452571868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42554765939712524},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4240737557411194},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.21145150065422058},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19575229287147522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15464523434638977},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":2,"locations":[{"id":"doi:10.21437/slate.2009-35","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-35","pdf_url":"https://www.isca-archive.org/slate_2009/suzuki09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.3793","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.3793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eee.bham.ac.uk/SLaTE2009/papers/SLaTE2009-21-v2.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/slate.2009-35","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-35","pdf_url":"https://www.isca-archive.org/slate_2009/suzuki09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2408444966.pdf","grobid_xml":"https://content.openalex.org/works/W2408444966.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W11805017","https://openalex.org/W15693373","https://openalex.org/W259925796","https://openalex.org/W1572136296","https://openalex.org/W2100012411","https://openalex.org/W2111148778","https://openalex.org/W2114492809","https://openalex.org/W2139008940","https://openalex.org/W2168862296","https://openalex.org/W2169878657","https://openalex.org/W2400884119","https://openalex.org/W2403379316"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W1553280128"],"abstract_inverted_index":{"Automatic":[0],"estimation":[1,83],"of":[2,21,113],"pronunciation":[3],"proficiency":[4,82],"has":[5],"its":[6],"specific":[7],"difficulty.":[8],"Adequacy":[9],"in":[10,86],"controlling":[11],"the":[12,25,44,65,90,95],"vocal":[13],"organs":[14],"is":[15],"often":[16],"estimated":[17],"from":[18],"spectral":[19],"envelopes":[20],"input":[22],"utterances":[23],"but":[24,103],"envelope":[26,45],"patterns":[27],"are":[28],"also":[29,72,138],"affected":[30],"by":[31,48,53],"alternating":[32],"speakers.":[33],"To":[34],"develop":[35],"a":[36,81,110,123,126],"good":[37],"and":[38,51,118,125,134,137],"stable":[39],"method":[40],"for":[41,73,94],"automatic":[42],"estimation,":[43],"changes":[46],"caused":[47],"linguistic":[49],"factors":[50,55],"those":[52],"extra-linguistic":[54],"should":[56],"be":[57],"properly":[58],"separated.":[59],"In":[60,75],"our":[61],"previous":[62],"study":[63],"After":[64],"proposal,":[66],"we":[67,78,97,108],"have":[68],"tested":[69],"that":[70,100],"representation":[71],"ASR":[74],"this":[76],"paper,":[77],"focus":[79],"on":[80],"experiment":[84,101],"done":[85],"[1]":[87],"and,":[88],"using":[89],"recently":[91],"developed":[92],"techniques":[93],"structures,":[96],"carry":[98],"out":[99],"again":[102],"under":[104],"different":[105],"conditions.":[106],"Here,":[107],"use":[109],"smaller":[111],"unit":[112],"structural":[114,120],"analysis,":[115],"speaker-invariant":[116],"substructures,":[117],"relative":[119],"distances":[121],"between":[122,132],"learner":[124],"teacher.":[127],"Results":[128],"show":[129,139],"higher":[130,141],"correlation":[131],"human":[133],"machine":[135],"rating":[136],"extremely":[140],"robustness":[142],"to":[143,147],"speaker":[144],"differences":[145],"compared":[146],"widely":[148],"used":[149],"GOP":[150],"scores.":[151]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
