{"id":"https://openalex.org/W2288990489","doi":"https://doi.org/10.1109/apsipa.2015.7415425","title":"Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN","display_name":"Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288990489","doi":"https://doi.org/10.1109/apsipa.2015.7415425","mag":"2288990489"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5076754533","display_name":"Hiroki Kanagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Kanagawa","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022767796","display_name":"Yuuki Tachioka","orcid":"https://orcid.org/0009-0002-0587-2943"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuuki Tachioka","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, US","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055378566","display_name":"Jun Ishii","orcid":"https://orcid.org/0000-0003-2568-515X"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Ishii","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7807,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89299344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"263","issue":null,"first_page":"86","last_page":"92"},"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":0.9987000226974487,"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/transformation","display_name":"Transformation (genetics)","score":0.7007808089256287},{"id":"https://openalex.org/keywords/transformation-matrix","display_name":"Transformation matrix","score":0.6484176516532898},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5984811186790466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5685133934020996},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5457398891448975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5183092951774597},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5134649872779846},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5132474899291992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5016908645629883},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4920958876609802},{"id":"https://openalex.org/keywords/linear-map","display_name":"Linear map","score":0.45832905173301697},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4400450587272644},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.41769057512283325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3660077750682831},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3394460678100586},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.09527024626731873},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08582010865211487}],"concepts":[{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7007808089256287},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.6484176516532898},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5984811186790466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5685133934020996},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5457398891448975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5183092951774597},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5134649872779846},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5132474899291992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016908645629883},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4920958876609802},{"id":"https://openalex.org/C49766605","wikidata":"https://www.wikidata.org/wiki/Q207643","display_name":"Linear map","level":2,"score":0.45832905173301697},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4400450587272644},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.41769057512283325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3660077750682831},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3394460678100586},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.09527024626731873},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08582010865211487},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W31925794","https://openalex.org/W112154549","https://openalex.org/W156213964","https://openalex.org/W159523117","https://openalex.org/W1487851247","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1537275613","https://openalex.org/W1599512239","https://openalex.org/W1984570643","https://openalex.org/W2002342963","https://openalex.org/W2044048547","https://openalex.org/W2081976287","https://openalex.org/W2087006792","https://openalex.org/W2101045344","https://openalex.org/W2106554350","https://openalex.org/W2112739286","https://openalex.org/W2116813507","https://openalex.org/W2121981798","https://openalex.org/W2122677231","https://openalex.org/W2134218976","https://openalex.org/W2146871184","https://openalex.org/W2152051032","https://openalex.org/W2153914468","https://openalex.org/W2160373860","https://openalex.org/W2187166234","https://openalex.org/W2328757576","https://openalex.org/W2962719052","https://openalex.org/W3042359118","https://openalex.org/W6601314542","https://openalex.org/W6604513159","https://openalex.org/W6606552489","https://openalex.org/W6631362777","https://openalex.org/W6683676920","https://openalex.org/W6687050748","https://openalex.org/W6702079475","https://openalex.org/W6780788142"],"related_works":["https://openalex.org/W2532418359","https://openalex.org/W4399588630","https://openalex.org/W3021551309","https://openalex.org/W3182134048","https://openalex.org/W4313165766","https://openalex.org/W3161907465","https://openalex.org/W4239093923","https://openalex.org/W2791356554","https://openalex.org/W2113663012","https://openalex.org/W2094613789"],"abstract_inverted_index":{"Feature-space":[0],"maximum-likelihood":[1],"linear":[2,187],"regression":[3,64,188],"(fMLLR)":[4],"transforms":[5],"acoustic":[6],"features":[7],"to":[8,45,89,110,125,148,165,175,195],"adapted":[9],"ones":[10],"by":[11],"a":[12,16,28,34,63,131,159,167,185],"multiplication":[13],"operation":[14],"with":[15],"single":[17,168],"transformation":[18,59,107,128,141,170],"matrix.":[19],"This":[20,122],"property":[21],"realizes":[22],"an":[23],"efficient":[24],"adaptation":[25,41,85,92,118,133],"performed":[26],"within":[27,130],"pre-precessing,":[29],"which":[30,66,190],"is":[31,120],"independent":[32],"of":[33,40,84,117,162],"decoding":[35,94,151],"process,":[36],"and":[37,93,153,156],"this":[38],"type":[39],"can":[42],"be":[43,87,111],"applied":[44,88],"deep":[46],"neural":[47],"network":[48],"(DNN).":[49],"On":[50],"the":[51,78,97,115,144,149,154,177,197,204],"other":[52],"hand,":[53],"constrained":[54],"MLLR":[55],"(CMLLR)":[56],"uses":[57],"multiple":[58,127,140],"matrices":[60,108,129,142,164],"based":[61],"on":[62],"tree,":[65],"provides":[67],"further":[68],"improvement":[69],"from":[70],"fMLLR.":[71,208],"However,":[72],"there":[73],"are":[74],"two":[75],"problems":[76],"in":[77,143],"model-space":[79],"adaptations:":[80],"first,":[81],"these":[82,163],"types":[83],"cannot":[86],"DNN":[90],"because":[91],"must":[95],"share":[96],"same":[98],"generative":[99],"model,":[100],"i.e.":[101],"Gaussian":[102],"mixture":[103],"model":[104],"(GMM).":[105],"Second,":[106],"tend":[109],"overly":[112],"fit":[113],"when":[114],"amount":[116],"data":[119],"small.":[121],"paper":[123],"proposes":[124],"use":[126],"feature-space":[132,182],"framework.":[134],"The":[135],"proposed":[136,205],"method":[137],"first":[138],"estimates":[139],"GMM":[145],"framework":[146],"according":[147],"first-pass":[150],"results":[152,201],"alignments,":[155],"then":[157],"takes":[158],"weighted":[160],"sum":[161],"obtain":[166],"feature":[169],"matrix":[171],"frame-by-frame.":[172],"In":[173],"addition,":[174],"address":[176],"second":[178],"problem,":[179],"we":[180],"propose":[181],"structural":[183],"maximum":[184],"posteriori":[186],"(fSMAPLR),":[189],"introduces":[191],"hierarchal":[192],"prior":[193],"distributions":[194],"regularize":[196],"MAP":[198],"estimation.":[199],"Experimental":[200],"show":[202],"that":[203],"fSMAPLR":[206],"outperformed":[207]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}