{"id":"https://openalex.org/W2403379316","doi":"https://doi.org/10.21437/slate.2007-24","title":"Are learners myna birds to the averaged distributions of native speakers? - a note ofwarning from a serious speech engineer -","display_name":"Are learners myna birds to the averaged distributions of native speakers? - a note ofwarning from a serious speech engineer -","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2403379316","doi":"https://doi.org/10.21437/slate.2007-24","mag":"2403379316"},"language":"en","primary_location":{"id":"doi:10.21437/slate.2007-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-24","pdf_url":"https://www.isca-archive.org/slate_2007/minematsu07_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 2007)","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_2007/minematsu07_slate.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo","Speech and Language Technology in Education (SLaTE2007) Farmington, PA, USA","Univ.\\ of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Speech and Language Technology in Education (SLaTE2007) Farmington, PA, USA","institution_ids":[]},{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041213266"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.551559,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86566695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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/utterance","display_name":"Utterance","score":0.8517963886260986},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7278220653533936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7084954977035522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7050001621246338},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6200212240219116},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5867471694946289},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4411989450454712},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4288385212421417},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.41885197162628174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3813250958919525},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3133120536804199},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3035178780555725}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8517963886260986},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7278220653533936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7084954977035522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050001621246338},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6200212240219116},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5867471694946289},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4411989450454712},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4288385212421417},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.41885197162628174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3813250958919525},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3133120536804199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3035178780555725},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/slate.2007-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-24","pdf_url":"https://www.isca-archive.org/slate_2007/minematsu07_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 2007)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/slate.2007-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2007-24","pdf_url":"https://www.isca-archive.org/slate_2007/minematsu07_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 2007)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2403379316.pdf","grobid_xml":"https://content.openalex.org/works/W2403379316.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W62463565","https://openalex.org/W125225111","https://openalex.org/W297015806","https://openalex.org/W2082557891","https://openalex.org/W2111882181","https://openalex.org/W2122989064","https://openalex.org/W2164770604","https://openalex.org/W2340304391","https://openalex.org/W3021823991","https://openalex.org/W4300584482"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W596245619","https://openalex.org/W2254895521","https://openalex.org/W2251422729"],"abstract_inverted_index":{"The":[0],"current":[1,157],"speech":[2,158,176],"recognition":[3],"technology":[4,159],"consists":[5],"of":[6,10,42,51],"clearly":[7],"separate":[8],"modules":[9],"acoustic":[11,25,40],"models,":[12,14],"language":[13,116],"a":[15,19,30,43,85,132,141,151,170],"pronunciation":[16],"dictionary,":[17],"and":[18,58,72,90,166],"decoder.CALL":[20],"systems":[21],"often":[22,77],"use":[23],"the":[24,34,38,81,94,98,156],"matching":[26],"module":[27],"to":[28,33,93,126,137],"compare":[29],"learner's":[31,86,142],"utterance":[32,87,143],"templates":[35,68],"stored":[36],"in":[37,140,150],"systems.The":[39],"template":[41],"phrase":[44,53],"is":[45,65,88,111],"usually":[46],"calculated":[47],"by":[48,55,174],"collecting":[49],"utterances":[50],"that":[52,155],"spoken":[54],"native":[56],"speakers":[57],"estimating":[59],"their":[60,119],"averaged":[61,95],"distribution.If":[62],"phoneme-based":[63,67],"comparison":[64],"required,":[66],"should":[69,144],"be":[70,145],"prepared":[71],"Hidden":[73],"Markov":[74],"Models":[75],"are":[76],"adopted":[78],"for":[79],"training":[80],"templates.In":[82],"this":[83,109,167],"framework,":[84],"acoustically":[89,146],"directly":[91],"compared":[92],"distributions.And":[96],"then,":[97],"notorious":[99],"mismatch":[100],"problem":[101],"more":[102],"or":[103],"less":[104],"inevitably":[105],"happens.I":[106],"wonder":[107],"whether":[108],"framework":[110],"pedagogically-sound":[112],"enough.No":[113],"children":[114],"acquire":[115],"through":[117],"imitating":[118],"parents'":[120],"voices":[121,129],"acoustically.Male":[122],"learners":[123],"don't":[124],"have":[125,162],"produce":[127],"female":[128,133],"even":[130],"when":[131],"teacher":[134],"asks":[135],"them":[136],"repeat":[138],"her.What":[139],"matched":[147],"with":[148],"what":[149],"teacher's":[152],"utterance?I":[153],"consider":[154],"does":[160],"not":[161],"any":[163],"good":[164,171],"answers":[165],"paper":[168],"proposes":[169],"candidate":[172],"answer":[173],"regarding":[175],"as":[177],"music.":[178]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}