{"id":"https://openalex.org/W2791636785","doi":"https://doi.org/10.1109/taslp.2018.2798821","title":"Context Adaptive Neural Network Based Acoustic Models for Rapid Adaptation","display_name":"Context Adaptive Neural Network Based Acoustic Models for Rapid Adaptation","publication_year":2018,"publication_date":"2018-01-26","ids":{"openalex":"https://openalex.org/W2791636785","doi":"https://doi.org/10.1109/taslp.2018.2798821","mag":"2791636785"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2798821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2798821","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2888-101X","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039041764","display_name":"Christian Huemmer","orcid":"https://orcid.org/0000-0002-4341-4217"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Huemmer","raw_affiliation_strings":["Chair of Multimedia Communications and Signal Processing, Friedrich-Alexander University Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4341-4217","affiliations":[{"raw_affiliation_string":"Chair of Multimedia Communications and Signal Processing, Friedrich-Alexander University Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.638,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87397985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"5","first_page":"895","last_page":"908"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech 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/computer-science","display_name":"Computer science","score":0.7563909292221069},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7342246770858765},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6848081350326538},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6492453217506409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6257445812225342},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.574059009552002},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5648714900016785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5445634722709656},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5164104104042053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479482501745224},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4445442855358124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43508586287498474},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4302041530609131},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4246801733970642},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4156950116157532},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09610077738761902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563909292221069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7342246770858765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6848081350326538},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6492453217506409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6257445812225342},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.574059009552002},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5648714900016785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5445634722709656},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5164104104042053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479482501745224},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4445442855358124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43508586287498474},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4302041530609131},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4246801733970642},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4156950116157532},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09610077738761902},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2798821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2798821","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G924316971","display_name":"Minimum Classification Error Criterion-based Development of Highly Discriminative Feature Space Associated with Optimal Class Boundary Search Methods","funder_award_id":"26280063","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W88864901","https://openalex.org/W330298975","https://openalex.org/W1487851247","https://openalex.org/W1493888297","https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1592672653","https://openalex.org/W1754457604","https://openalex.org/W1943324956","https://openalex.org/W1984570643","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2000629566","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2024490156","https://openalex.org/W2037740282","https://openalex.org/W2048526313","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2092845679","https://openalex.org/W2094147890","https://openalex.org/W2112021726","https://openalex.org/W2117239706","https://openalex.org/W2122272452","https://openalex.org/W2124776405","https://openalex.org/W2131342762","https://openalex.org/W2141778357","https://openalex.org/W2146871184","https://openalex.org/W2150769028","https://openalex.org/W2155648385","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2165108269","https://openalex.org/W2166547995","https://openalex.org/W2172097686","https://openalex.org/W2276408190","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2295119550","https://openalex.org/W2337992322","https://openalex.org/W2397381476","https://openalex.org/W2397725648","https://openalex.org/W2398776621","https://openalex.org/W2402201734","https://openalex.org/W2403731734","https://openalex.org/W2508162385","https://openalex.org/W2513664690","https://openalex.org/W2514021858","https://openalex.org/W2589099502","https://openalex.org/W2697254725","https://openalex.org/W2703224471","https://openalex.org/W2714726990","https://openalex.org/W2749510669","https://openalex.org/W3103256658","https://openalex.org/W3124056356","https://openalex.org/W4254582343","https://openalex.org/W6601563604","https://openalex.org/W6631362777","https://openalex.org/W6637567912"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W4206560911","https://openalex.org/W1970611213","https://openalex.org/W4372260270"],"abstract_inverted_index":{"The":[0,63,154,174,194],"adaptation":[1,75,105,228,248],"of":[2,44,65,76,80,106,110,133,149,156,166,169,171,249,265],"automatic":[3],"speech":[4,21],"recognition":[5,22],"systems":[6],"to":[7,18,37,59,69,215],"a":[8,111,128,147,163,250],"speaker":[9,55,227],"or":[10,39,56,151,177],"an":[11,45,95,142,191],"environment":[12],"is":[13,127,160],"important":[14],"if":[15],"we":[16,87],"are":[17,94,181],"achieve":[19,104],"high":[20],"performance":[23],"ubiquitously.":[24],"Recently,":[25],"deep":[26],"neural":[27,91,125,129,252],"network":[28,61,126,130,196,200,253],"(DNN)":[29],"based":[30,254],"acoustic":[31,50,143,255],"models":[32,232],"have":[33],"been":[34],"made":[35],"adaptive":[36,90,124],"speakers":[38,150],"environments":[40],"by":[41,187],"the":[42,49,60,70,74,77,81,108,114,119,157,167,172,184,198,207,212,263,266],"addition":[43,64],"auxiliary":[46,67,100,185,192,195],"feature":[47],"representing":[48,146],"context":[51,123,144,178,208],"information":[52],"such":[53,66],"as":[54,162],"noise":[57,152],"characteristics":[58],"input.":[62],"features":[68,101],"input":[71,82],"realizes":[72],"only":[73],"bias":[78,120],"term":[79],"layer.":[83],"In":[84],"this":[85],"paper,":[86],"introduce":[88],"\u201ccontext":[89],"networks,\u201d":[92],"which":[93,205],"alternative":[96],"approach":[97,268],"for":[98],"exploiting":[99],"that":[102,210],"can":[103,201],"all":[107,170],"parameters":[109],"layer":[112,159],"including":[113],"linear":[115],"transformation":[116],"matrices":[117],"and":[118,197,238,245],"terms.":[121],"A":[122],"with":[131,141,233,257],"one":[132,246],"its":[134],"layers":[135],"factorized":[136,158],"into":[137],"sublayers,":[138],"each":[139],"associated":[140],"class":[145,148,179],"conditions.":[153],"output":[155],"obtained":[161],"weighted":[164],"sum":[165],"contributions":[168],"sublayers.":[173],"weighting":[175],"coefficients,":[176],"weights,":[180],"derived":[182],"from":[183],"features,":[186],"transforming":[188],"them":[189],"through":[190],"network.":[193],"main":[199],"be":[202,216],"trained":[203],"jointly,":[204],"enables":[206],"classes":[209],"optimize":[211],"training":[213,243],"criterion":[214],"learned":[217],"automatically.":[218],"We":[219],"perform":[220],"experiments":[221,229,261],"on":[222],"three":[223],"tasks,":[224],"i.e.,":[225],"two":[226],"using":[230],"DNN":[231],"medium-sized":[234],"(Wall":[235],"Street":[236],"Journal)":[237],"large":[239],"(Continuous":[240],"Spontaneous":[241],"Japanese)":[242],"datasets,":[244],"environmental":[247],"convolutional":[251],"model":[256],"CHiME3":[258],"data.":[259],"These":[260],"confirm":[262],"potential":[264],"proposed":[267],"in":[269],"various":[270],"settings.":[271]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}