{"id":"https://openalex.org/W281219303","doi":"https://doi.org/10.21437/interspeech.2009-567","title":"On invariant structural representation for speech recognition: theoretical validation and experimental improvement","display_name":"On invariant structural representation for speech recognition: theoretical validation and experimental improvement","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W281219303","doi":"https://doi.org/10.21437/interspeech.2009-567","mag":"281219303"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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 University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, 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, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, 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":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3055","last_page":"3058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9984999895095825,"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":0.7309625744819641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6995168924331665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6842324733734131},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6101735830307007},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.583960235118866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5722506046295166},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5179352164268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174301266670227},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4919893443584442},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.46273598074913025},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4365575313568115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26838210225105286}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7309625744819641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6995168924331665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6842324733734131},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6101735830307007},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.583960235118866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5722506046295166},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5179352164268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174301266670227},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4919893443584442},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.46273598074913025},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4365575313568115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26838210225105286},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W15693373","https://openalex.org/W64921504","https://openalex.org/W1489972948","https://openalex.org/W2111148778","https://openalex.org/W2112638956","https://openalex.org/W2114492809","https://openalex.org/W2115606020","https://openalex.org/W2132549764","https://openalex.org/W2135346934","https://openalex.org/W2168862296","https://openalex.org/W2169878657","https://openalex.org/W3127518054"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W1748856376","https://openalex.org/W259157601"],"abstract_inverted_index":{"One":[0],"of":[1,25,44,84,87,94,131,153],"the":[2,31,39,60,68,105,110,132,145,150,180,189],"most":[3],"challenging":[4],"problems":[5],"in":[6],"speech":[7,26,45],"recognition":[8,123,136,151],"is":[9,127,183],"to":[10,67,89,156,173],"deal":[11,90],"with":[12,91],"inevitable":[13],"acoustic":[14],"variations":[15,33],"caused":[16],"by":[17],"nonlinguistic":[18],"factors.":[19],"Recently,":[20],"an":[21],"invariant":[22,196],"structural":[23,70,95,154,167],"representation":[24],"was":[27],"proposed":[28,111,119,181],"[1],":[29],"where":[30],"non-linguistic":[32],"are":[34],"effectively":[35],"removed":[36],"though":[37],"modeling":[38],"dynamic":[40],"and":[41,75,100,141],"contrastive":[42],"aspects":[43],"signals.":[46],"This":[47],"paper":[48],"describes":[49],"our":[50],"recent":[51],"progresses":[52],"on":[53],"this":[54],"problem.":[55],"Theoretically,":[56],"we":[57,80,108,148],"prove":[58],"that":[59,166],"maximum":[61],"likelihood":[62],"based":[63,135],"decomposition":[64],"can":[65],"lead":[66],"same":[69],"representations":[71,155,168],"for":[72],"a":[73,82,122],"sequence":[74],"its":[76],"transformed":[77],"version.":[78],"Practically,":[79],"introduce":[81],"method":[83,112,120,182],"discriminant":[85],"analysis":[86,200],"eigen-structure":[88],"two":[92],"limitations":[93],"representations,":[96],"namely,":[97],"high":[98],"dimensionality":[99],"too":[101],"strong":[102],"invariance.":[103],"In":[104,144],"1st":[106],"experiment,":[107,147],"evaluate":[109],"through":[113],"recognizing":[114],"connected":[115],"Japanese":[116],"vowels.":[117],"The":[118,162],"achieves":[121],"rate":[124],"99.0%,":[125],"which":[126],"higher":[128],"than":[129,176,188],"those":[130],"previous":[133,190],"structure":[134],"methods":[137],"[2,":[138],"3,":[139],"4]":[140],"word":[142],"HMM.":[143,177],"2nd":[146],"examine":[149],"performance":[152],"vocal":[157],"tract":[158],"length":[159],"(VTL)":[160],"differences.":[161],"experimental":[163],"results":[164],"indicate":[165],"have":[169],"much":[170],"more":[171],"robustness":[172],"VTL":[174],"changes":[175],"w":[178],"Moreover,":[179],"about":[184],"60":[185],"times":[186],"faster":[187],"ones.":[191],"Index":[192],"Terms:":[193],"Speech":[194],"recognition,":[195],"structure,":[197],"PCA,":[198],"discriminative":[199]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"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"}