{"id":"https://openalex.org/W2397725648","doi":"https://doi.org/10.1109/icassp.2016.7472683","title":"Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions","display_name":"Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397725648","doi":"https://doi.org/10.1109/icassp.2016.7472683","mag":"2397725648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":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/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/A5040951732","display_name":"Chengzhu Yu","orcid":null},"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"]},{"id":"https://openalex.org/I87573096","display_name":"University of North Texas at Dallas","ror":"https://ror.org/01n51v443","country_code":"US","type":"education","lineage":["https://openalex.org/I87573096"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","NTT, University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT, University of Texas at Dallas","institution_ids":["https://openalex.org/I87573096"]}]},{"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":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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"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":"Takuya Yoshioka","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":"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":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5270","last_page":"5274"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9993000030517578,"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":0.7772819995880127},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6950931549072266},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6563806533813477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6384727954864502},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.582690954208374},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4878551959991455},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4865330755710602},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4777630865573883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4679720997810364},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4598004221916199},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4457877576351166},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4454788863658905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4238145351409912},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20655325055122375},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0521012544631958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772819995880127},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6950931549072266},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6563806533813477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384727954864502},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.582690954208374},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4878551959991455},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4865330755710602},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4777630865573883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4679720997810364},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4598004221916199},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4457877576351166},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4454788863658905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4238145351409912},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20655325055122375},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0521012544631958},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W185613617","https://openalex.org/W567546468","https://openalex.org/W1487851247","https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1984570643","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W1993882792","https://openalex.org/W2010362084","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2062164080","https://openalex.org/W2066334462","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2117239706","https://openalex.org/W2124776405","https://openalex.org/W2155648385","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2401144871","https://openalex.org/W2402201734","https://openalex.org/W2405505124","https://openalex.org/W2406373047","https://openalex.org/W2407146636","https://openalex.org/W4244494905","https://openalex.org/W4254582343","https://openalex.org/W6603403951","https://openalex.org/W6607553906","https://openalex.org/W6615969787","https://openalex.org/W6631362777","https://openalex.org/W6712525707","https://openalex.org/W6713383670","https://openalex.org/W6713448032","https://openalex.org/W6713583293","https://openalex.org/W6713806900"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1533421371","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2086773623"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"based":[4],"acoustic":[5,32,70,100],"models":[6],"have":[7,23,55],"greatly":[8],"improved":[9],"the":[10,31,45,69,112,116,119,126,133,140,152,156,160,165,169,183,190],"performance":[11,21],"of":[12,30,95,105,118,139,155,192],"automatic":[13],"speech":[14,186],"recognition":[15,187],"(ASR)":[16],"for":[17,38,176,195],"various":[18],"tasks.":[19],"Further":[20],"improvements":[22],"been":[24],"reported":[25],"when":[26],"making":[27],"DNNs":[28],"aware":[29],"context":[33,59,71,101,121,127],"(e.g.":[34],"speaker":[35,52],"or":[36,51,84],"environment)":[37],"example":[39],"by":[40,111,150],"adding":[41],"auxiliary":[42],"features":[43],"to":[44,67,97],"input,":[46],"such":[47],"as":[48],"noise":[49],"estimates":[50],"i-vectors.":[53],"We":[54,178],"recently":[56],"proposed":[57],"a":[58,74,79,92,106],"adaptive":[60],"DNN":[61,80],"(CA-DNN),":[62],"which":[63],"is":[64,78,109],"another":[65],"approach":[66,194],"exploit":[68],"information":[72],"within":[73],"DNN.":[75],"A":[76],"CA-DNN":[77,157],"that":[81,90],"has":[82],"one":[83],"several":[85],"factorized":[86,107],"layers,":[87],"i.e.":[88],"layers":[89],"use":[91],"different":[93,120],"set":[94],"parameters":[96,158],"process":[98],"each":[99],"class.":[102],"The":[103],"output":[104],"layer":[108],"obtained":[110],"weighted":[113],"sum":[114],"over":[115,125],"contribution":[117],"classes,":[122],"given":[123],"weights":[124,135,162,167],"classes.":[128],"In":[129,142],"our":[130,147,193],"previous":[131,148],"work,":[132],"class":[134,161,166,171],"were":[136],"computed":[137],"independently":[138],"recognizer.":[141],"this":[143],"paper,":[144],"we":[145],"extend":[146],"work":[149],"introducing":[151],"joint":[153],"training":[154],"and":[159,168],"computation.":[163],"Consequently,":[164],"associated":[170],"definitions":[172],"can":[173],"be":[174],"optimized":[175],"ASR.":[177],"report":[179],"experimental":[180],"results":[181],"on":[182],"AURORA4":[184],"noisy":[185],"task":[188],"showing":[189],"potential":[191],"fast":[196],"unsupervised":[197],"adaptation.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}