{"id":"https://openalex.org/W1571447047","doi":"https://doi.org/10.1109/icassp.2015.7178829","title":"Context adaptive deep neural networks for fast acoustic model adaptation","display_name":"Context adaptive deep neural networks for fast acoustic model adaptation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1571447047","doi":"https://doi.org/10.1109/icassp.2015.7178829","mag":"1571447047"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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","NTT Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan"],"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 Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 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","NTT Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan"],"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 Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"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":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","NTT Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan"],"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 Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 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","NTT Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan"],"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 Communication Science Laboratories, NTT corporation, 2-4, Hikaridai, Seika-cho (Keihanna Science City), Soraku-gun, Kyoto 619-0237 Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4535","last_page":"4539"},"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758625745773315},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6906805038452148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6600978970527649},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5957087278366089},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5918626189231873},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5870028734207153},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5337399244308472},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4823574423789978},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45080679655075073},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44199711084365845},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4385390877723694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3901696801185608},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3726956248283386},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3415810167789459},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18245568871498108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758625745773315},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6906805038452148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6600978970527649},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5957087278366089},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5918626189231873},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5870028734207153},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5337399244308472},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4823574423789978},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45080679655075073},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44199711084365845},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4385390877723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3901696801185608},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3726956248283386},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3415810167789459},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18245568871498108},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/icassp.2015.7178829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"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":32,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W185613617","https://openalex.org/W567546468","https://openalex.org/W1513862252","https://openalex.org/W1984570643","https://openalex.org/W1989549063","https://openalex.org/W1993882792","https://openalex.org/W2010362084","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2058641082","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2084894614","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2117239706","https://openalex.org/W2124776405","https://openalex.org/W2146871184","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2172097686","https://openalex.org/W2394967684","https://openalex.org/W2395596777","https://openalex.org/W2403731734","https://openalex.org/W3127686677","https://openalex.org/W4244494905","https://openalex.org/W4254582343","https://openalex.org/W6607553906","https://openalex.org/W6615969787","https://openalex.org/W6711726519"],"related_works":["https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W1694601526","https://openalex.org/W128188896"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4],"widely":[5],"used":[6],"for":[7,76],"acoustic":[8,47,83,87,107],"modeling":[9],"in":[10,38],"automatic":[11],"speech":[12],"recognition":[13,173],"(ASR),":[14],"since":[15],"they":[16],"greatly":[17],"outperform":[18],"legacy":[19],"Gaussian":[20],"mixture":[21],"model-based":[22],"systems.":[23],"However,":[24],"the":[25,43,77,86,106,133,143,146,153,159,170,179],"levels":[26],"of":[27,80,122,128,132,145,161],"performance":[28],"achieved":[29],"by":[30,112,139],"current":[31],"DNN-based":[32,82],"systems":[33],"remain":[34],"far":[35],"too":[36],"low":[37],"many":[39],"tasks,":[40],"e.g.":[41],"when":[42],"training":[44],"and":[45,165],"testing":[46],"contexts":[48],"differ":[49],"due":[50],"to":[51,85,124],"ambient":[52],"noise,":[53],"reverberation":[54],"or":[55,97],"speaker":[56],"variability.":[57],"Consequently,":[58],"research":[59],"on":[60,101],"DNN":[61,94,164],"adaptation":[62,79],"has":[63],"recently":[64],"attracted":[65],"much":[66],"interest.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"present":[72],"a":[73,81,91,114,119],"novel":[74],"approach":[75],"fast":[78],"model":[84],"context.":[88],"We":[89],"introduce":[90],"context":[92,162],"adaptive":[93,163],"with":[95,169,178],"one":[96],"several":[98],"layers":[99],"depending":[100],"external":[102],"factors":[103],"that":[104,117],"represent":[105],"conditions.":[108],"This":[109,156],"is":[110,136],"realized":[111],"introducing":[113],"factorized":[115,134],"layer":[116,135],"uses":[118],"different":[120,147],"set":[121],"parameters":[123],"process":[125],"each":[126],"class":[127],"factors.":[129],"The":[130],"output":[131],"then":[137],"obtained":[138],"weighted":[140],"averaging":[141],"over":[142,152],"contribution":[144],"factor":[148,154],"classes,":[149],"given":[150],"posteriors":[151],"classes.":[155],"paper":[157],"introduces":[158],"concept":[160],"describes":[166],"preliminary":[167],"experiments":[168],"TIMIT":[171],"phoneme":[172],"task":[174],"showing":[175],"consistent":[176],"improvement":[177],"proposed":[180],"approach.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}