{"id":"https://openalex.org/W2111148778","doi":"https://doi.org/10.1109/asru.2007.4430176","title":"Random discriminant structure analysis for automatic recognition of connected vowels","display_name":"Random discriminant structure analysis for automatic recognition of connected vowels","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2111148778","doi":"https://doi.org/10.1109/asru.2007.4430176","mag":"2111148778"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"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":"Yu Qiao","raw_affiliation_strings":["The Graduate School of Frontier Sciences, University of Tokyo, Japan","University of Tokyo, Tokyo,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo, Tokyo,","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103581782","display_name":"Satoshi Asakawa","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":"Satoshi Asakawa","raw_affiliation_strings":["The Graduate School of Frontier Sciences, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate School of Frontier Sciences, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","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 Graduate School of Frontier Sciences, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate School of Frontier Sciences, University of Tokyo, 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":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"576","last_page":"581"},"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":0.9988999962806702,"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":0.9980999827384949,"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/discriminative-model","display_name":"Discriminative model","score":0.863092303276062},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7433447241783142},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.6871576309204102},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6837406158447266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6726404428482056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6645670533180237},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6291043758392334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5842016935348511},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4681646525859833},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.44933032989501953},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.442484050989151},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.43846794962882996},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.42262402176856995}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.863092303276062},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7433447241783142},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6871576309204102},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6837406158447266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726404428482056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6645670533180237},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6291043758392334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5842016935348511},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4681646525859833},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.44933032989501953},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.442484050989151},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.43846794962882996},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.42262402176856995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2007.4430176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.9591","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.9591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~qiao/publish/asru07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.431.7575","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.431.7575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2007/ASRU_p576-581_t2007-12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W297015806","https://openalex.org/W1489972948","https://openalex.org/W1746680969","https://openalex.org/W1986317063","https://openalex.org/W2027915610","https://openalex.org/W2100969003","https://openalex.org/W2103632967","https://openalex.org/W2112638956","https://openalex.org/W2113242816","https://openalex.org/W2115606020","https://openalex.org/W2120070835","https://openalex.org/W2132549764","https://openalex.org/W2135346934","https://openalex.org/W2146871184","https://openalex.org/W2156172072","https://openalex.org/W2157124852","https://openalex.org/W2169878657","https://openalex.org/W2799061466","https://openalex.org/W2907162034","https://openalex.org/W4205687621","https://openalex.org/W4299681030","https://openalex.org/W6610627759","https://openalex.org/W6629462044","https://openalex.org/W6678054285"],"related_works":["https://openalex.org/W2350751952","https://openalex.org/W1999647744","https://openalex.org/W2362114017","https://openalex.org/W2114217318","https://openalex.org/W2794812819","https://openalex.org/W2120164251","https://openalex.org/W3147024994","https://openalex.org/W2587881214","https://openalex.org/W3104072235","https://openalex.org/W2063246903"],"abstract_inverted_index":{"The":[0],"universal":[1],"structure":[2,31,63],"of":[3,26,29,52,118,143,150,159,165],"speech":[4,23],"[1,":[5],"2],":[6],"proves":[7],"to":[8,11,35,66,94],"be":[9],"invariant":[10],"transformations":[12],"in":[13],"feature":[14,89],"space,":[15],"and":[16,81,91,99,115],"thus":[17],"provides":[18],"a":[19,140],"robust":[20],"representation":[21,32,114],"for":[22,112,123],"recognition.":[24],"One":[25],"the":[27,50,73,85,116,124,147,163],"difficulties":[28],"using":[30],"is":[33,110,154],"due":[34],"its":[36],"high":[37],"dimensionality.":[38],"This":[39],"not":[40],"only":[41],"increases":[42],"computational":[43],"cost":[44],"but":[45],"also":[46],"easily":[47],"suffers":[48],"from":[49,102],"curse":[51],"dimensionality":[53],"[3,":[54],"4].":[55],"In":[56],"this":[57,69],"paper,":[58],"we":[59],"introduce":[60],"random":[61,88],"discriminant":[62],"analysis":[64,93],"(RDSA)":[65],"deal":[67],"with":[68,162],"problem.":[70],"Based":[71],"on":[72,130,146],"observation":[74],"that":[75,136,157],"structural":[76],"features":[77],"are":[78,121],"highly":[79],"correlated":[80],"include":[82],"large":[83],"redundancy,":[84],"RDSA":[86],"combines":[87],"selection":[90],"discriminative":[92,100],"calculate":[95],"several":[96],"low":[97],"dimensional":[98],"representations":[101],"an":[103,107],"input":[104],"structure.":[105],"Then":[106],"individual":[108],"classifier":[109,120],"trained":[111,161],"each":[113,119],"outputs":[117],"integrated":[122],"final":[125],"classification":[126],"decision.":[127],"Experimental":[128],"results":[129],"connected":[131],"Japanese":[132],"vowel":[133],"utterances":[134,164],"show":[135],"our":[137],"approach":[138],"achieves":[139],"recognition":[141],"rate":[142],"98.3%":[144],"based":[145],"training":[148],"data":[149],"8":[151],"speakers,":[152],"which":[153],"higher":[155],"than":[156],"(97.4%)":[158],"HMMs":[160],"4,130":[166],"speakers.":[167]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}