{"id":"https://openalex.org/W2128575093","doi":"https://doi.org/10.1109/icassp.2009.4960662","title":"Affine invariant features and their application to speech recognition","display_name":"Affine invariant features and their application to speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2128575093","doi":"https://doi.org/10.1109/icassp.2009.4960662","mag":"2128575093"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":true,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Graduate School of Engineering, University of Tokyo, Tokyo, Japan","Graduate school of Engineering, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","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":["Graduate School of Engineering, University of Tokyo, Tokyo, Japan","Graduate school of Engineering, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of Engineering, The 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":["Graduate School of Engineering, University of Tokyo, Tokyo, Japan","Graduate school of Engineering, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate school of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100748135"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8533964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"4629","last_page":"4632"},"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":0.9983000159263611,"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":0.9976000189781189,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9035104513168335},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7498950958251953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.651765763759613},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6031337976455688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5841180086135864},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5333357453346252},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5049658417701721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4899112582206726},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.44885018467903137},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4446297883987427},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31083881855010986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2856273949146271}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9035104513168335},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7498950958251953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.651765763759613},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6031337976455688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841180086135864},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5333357453346252},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5049658417701721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899112582206726},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.44885018467903137},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4446297883987427},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31083881855010986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2856273949146271},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.422","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/2009/ICASSP_p4629-4632_t2009-4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1592510033","https://openalex.org/W1971332722","https://openalex.org/W1983496390","https://openalex.org/W2032420816","https://openalex.org/W2037740282","https://openalex.org/W2046176189","https://openalex.org/W2055755574","https://openalex.org/W2100969003","https://openalex.org/W2104559592","https://openalex.org/W2111148778","https://openalex.org/W2115606020","https://openalex.org/W2117419877","https://openalex.org/W2121014056","https://openalex.org/W2140567543","https://openalex.org/W2164931619","https://openalex.org/W2168862296","https://openalex.org/W2169878657","https://openalex.org/W3103439176","https://openalex.org/W6674919975","https://openalex.org/W6684964546"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W2335896301","https://openalex.org/W2330863229","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W2137764249","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W3006618853","https://openalex.org/W2154472250"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"set":[4],"of":[5,67,81,83,101],"affine":[6,28,60],"invariant":[7],"features":[8,72],"(AIFs)":[9],"for":[10,73,89],"sequence":[11,22,69],"data.":[12],"The":[13,94,141],"proposed":[14],"AIFs":[15,39,66,82,88,102,126,142],"can":[16,55,107,127],"be":[17,56],"calculated":[18],"directly":[19],"from":[20],"the":[21,38,44,65,79,99,120,123,129],"data,":[23],"and":[24,86],"their":[25,153],"invariance":[26,80,154],"to":[27,40,51,109,136,145],"transformation":[29],"is":[30,155],"proved":[31],"mathematically":[32],"through":[33],"algebraic":[34],"calculation.":[35],"We":[36,76],"apply":[37,87],"speech":[41,84,150],"recognition.":[42,93],"Since":[43],"vocal":[45],"tract":[46],"length":[47],"(VTL)":[48],"difference":[49],"causes":[50],"frequency":[52],"warping":[53],"which":[54],"approximated":[57],"well":[58],"by":[59],"transform":[61],"on":[62],"cepstral":[63,68],"features,":[64],"provide":[70],"robust":[71],"VTL":[74],"variations.":[75],"experimentally":[77],"examine":[78],"signals,":[85],"Japanese":[90],"isolated":[91],"word":[92],"experimental":[95],"results":[96],"show":[97],"that":[98],"combination":[100,124],"with":[103,125],"MFCC":[104,114,137],"or":[105,115,138],"MFCC+Delta":[106,116,139],"lead":[108],"higher":[110],"recognition":[111],"rates":[112,131],"than":[113,149],"only.":[117,140],"Especially":[118],"in":[119],"mismatched":[121],"experiments,":[122],"reduce":[128],"error":[130],"about":[132],"30%":[133],"when":[134],"compared":[135],"are":[143],"expected":[144],"have":[146],"other":[147],"applications":[148],"recognition,":[151],"since":[152],"general.":[156]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}