{"id":"https://openalex.org/W2164805947","doi":"https://doi.org/10.1109/tsp.2010.2047340","title":"A Study on Invariance of $f$-Divergence and Its Application to Speech Recognition","display_name":"A Study on Invariance of $f$-Divergence and Its Application to Speech Recognition","publication_year":2010,"publication_date":"2010-04-05","ids":{"openalex":"https://openalex.org/W2164805947","doi":"https://doi.org/10.1109/tsp.2010.2047340","mag":"2164805947"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2010.2047340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2010.2047340","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-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/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy and Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy and Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"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 Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6432,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98060754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"58","issue":"7","first_page":"3884","last_page":"3890"},"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":0.9987999796867371,"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":0.9954000115394592,"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/invariant","display_name":"Invariant (physics)","score":0.6777766942977905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49083811044692993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4767937660217285},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.46844321489334106},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4532450735569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.448309987783432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4356728792190552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4238627552986145},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4180009663105011},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34224429726600647},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.2679345905780792}],"concepts":[{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6777766942977905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49083811044692993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4767937660217285},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.46844321489334106},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4532450735569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.448309987783432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4356728792190552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4238627552986145},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4180009663105011},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34224429726600647},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.2679345905780792},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1109/tsp.2010.2047340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2010.2047340","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W12737881","https://openalex.org/W15693373","https://openalex.org/W64921504","https://openalex.org/W152055444","https://openalex.org/W281219303","https://openalex.org/W638747377","https://openalex.org/W1770825568","https://openalex.org/W1973375658","https://openalex.org/W2033178790","https://openalex.org/W2055309977","https://openalex.org/W2111148778","https://openalex.org/W2114492809","https://openalex.org/W2115606020","https://openalex.org/W2131940723","https://openalex.org/W2135346934","https://openalex.org/W2143899172","https://openalex.org/W2152321560","https://openalex.org/W2156172072","https://openalex.org/W2168862296","https://openalex.org/W2168961642","https://openalex.org/W2169878657","https://openalex.org/W3127518054","https://openalex.org/W4293404332","https://openalex.org/W6600524859","https://openalex.org/W6684964546"],"related_works":["https://openalex.org/W3198942245","https://openalex.org/W1981379995","https://openalex.org/W2606926094","https://openalex.org/W2086671596","https://openalex.org/W2136763963","https://openalex.org/W2784044004","https://openalex.org/W2783045591","https://openalex.org/W2109705048","https://openalex.org/W2025991752","https://openalex.org/W2539985974"],"abstract_inverted_index":{"Identifying":[0],"features":[1],"invariant":[2,33,92,115,140],"to":[3,34,41,63,89,117,129],"certain":[4],"transformations":[5],"is":[6],"a":[7,22,149],"fundamental":[8],"problem":[9],"in":[10,71],"the":[11,49,54,104,131,139],"fields":[12],"of":[13,24,53,56,106,113,156],"signal":[14],"processing":[15],"and":[16,37,51,74,81,102],"pattern":[17],"recognition.":[18,43],"This":[19],"correspondence":[20],"explores":[21],"family":[23],"measures":[25],"called":[26],"<i":[27,57,67],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,58,68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">f</i>":[29,59,69],"-divergences":[30,70],"that":[31,138],"are":[32,84],"invertible":[35],"transformations,":[36],"studies":[38],"their":[39],"application":[40,112],"speech":[42,157],"We":[44,86,109],"provide":[45],"novel":[46],"proofs":[47],"for":[48,75,153],"sufficiency":[50],"necessity":[52],"invariance":[55,105],"-divergence.":[60],"Several":[61],"techniques":[62,128],"calculate":[64],"or":[65],"approximate":[66],"general":[72],"cases":[73],"special":[76],"distributions":[77],"such":[78],"as":[79],"Gaussian":[80,82],"mixture":[83],"reviewed.":[85],"show":[87,137],"how":[88],"construct":[90],"an":[91,111],"structural":[93],"representation":[94,116],"from":[95],"sequence":[96],"data":[97],"through":[98],"maximum":[99],"likelihood":[100],"decomposition,":[101],"prove":[103],"this":[107,114],"decomposition.":[108],"demonstrate":[110],"recognizing":[118],"connected":[119],"Japanese":[120],"vowel":[121],"utterances.":[122],"In":[123],"addition,":[124],"we":[125],"propose":[126],"several":[127],"improve":[130],"recognition":[132],"performance.":[133],"The":[134],"experimental":[135],"results":[136],"structure":[141],"achieves":[142],"better":[143],"performance":[144],"than":[145],"hidden":[146],"Markov":[147],"models,":[148],"widely":[150],"used":[151],"technique":[152],"acoustic":[154],"modeling":[155],"sounds.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}