{"id":"https://openalex.org/W2112021726","doi":"https://doi.org/10.1109/taslp.2014.2346313","title":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","display_name":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","publication_year":2014,"publication_date":"2014-08-08","ids":{"openalex":"https://openalex.org/W2112021726","doi":"https://doi.org/10.1109/taslp.2014.2346313","mag":"2112021726"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2346313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2346313","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/A5083184776","display_name":"Shaofei Xue","orcid":"https://orcid.org/0000-0001-6199-7965"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Xue","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University, Toronto, Canada","Department of Electrical Engineering and Computer Science; York University; Toronto ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science; York University; Toronto ON Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779276","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-2718-9811"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University, Toronto, Canada","Department of Electrical Engineering and Computer Science; York University; Toronto ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science; York University; Toronto ON Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019919993","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0003-1313-9418"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.9217,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":{"value":0.99633946,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"12","first_page":"1713","last_page":"1725"},"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":0.9995999932289124,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.777521014213562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7542898654937744},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6656455397605896},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5927190780639648},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5197136402130127},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5189016461372375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5072967410087585},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46582552790641785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46323105692863464},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4117235541343689},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2872983515262604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777521014213562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7542898654937744},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6656455397605896},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5927190780639648},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5197136402130127},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5189016461372375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072967410087585},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46582552790641785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46323105692863464},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4117235541343689},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2872983515262604},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2346313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2346313","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":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1513862252","https://openalex.org/W1599512239","https://openalex.org/W1975138161","https://openalex.org/W1987238397","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W1993882792","https://openalex.org/W1998656041","https://openalex.org/W2002016471","https://openalex.org/W2010362084","https://openalex.org/W2016084804","https://openalex.org/W2036351241","https://openalex.org/W2046899276","https://openalex.org/W2063689849","https://openalex.org/W2076794394","https://openalex.org/W2077804127","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2081884280","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2100969003","https://openalex.org/W2106119541","https://openalex.org/W2110798204","https://openalex.org/W2112739286","https://openalex.org/W2117824967","https://openalex.org/W2121981798","https://openalex.org/W2122272452","https://openalex.org/W2136836257","https://openalex.org/W2136922672","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2156692643","https://openalex.org/W2160306971","https://openalex.org/W2394932179","https://openalex.org/W2403731734","https://openalex.org/W6603403951","https://openalex.org/W6676481782"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W4255044973","https://openalex.org/W2262333520","https://openalex.org/W2499802997","https://openalex.org/W1995562189","https://openalex.org/W2112059504"],"abstract_inverted_index":{"Fast":[0],"adaptation":[1,23,68,76,88,95,120,138,158,201,214,230,248],"of":[2,39,47,139,200,229],"deep":[3,13],"neural":[4,267],"networks":[5,268],"(DNN)":[6],"is":[7,90,254],"an":[8],"important":[9],"research":[10],"topic":[11],"in":[12,96,132,160,175,241,244,262],"learning.":[14],"In":[15,83],"this":[16,84,119,263],"paper,":[17],"we":[18,51,235],"have":[19,112,154,181,208,236],"proposed":[20,113,157,212],"a":[21,40,44,197,226],"general":[22],"scheme":[24,89,121],"for":[25,78,269],"DNN":[26,42,140,193],"based":[27,99,122,141],"on":[28,100,123,142],"discriminant":[29],"condition":[30,73],"codes,":[31],"which":[32,253],"are":[33,187],"directly":[34],"fed":[35],"to":[36,56,70,92,117,190,219,257],"various":[37],"layers":[38],"pre-trained":[41],"through":[43],"new":[45,72,80],"set":[46],"connection":[48,58],"weights.":[49],"Moreover,":[50],"present":[52],"several":[53],"training":[54,61,109,149,251],"methods":[55,69,159,186,215],"learn":[57,71],"weights":[59],"from":[60,75],"data":[62,77],"as":[63,65],"well":[64],"the":[66,86,124,156,176,205,211,258],"corresponding":[67],"code":[74],"each":[79],"test":[81],"condition.":[82],"work,":[85],"fast":[87],"applied":[91],"supervised":[93],"speaker":[94,126,143,147,151,247],"speech":[97,163,173],"recognition":[98,164,169,174],"either":[101],"frame-level":[102],"cross-entropy":[103],"or":[104],"sequence-level":[105],"maximum":[106],"mutual":[107],"information":[108],"criterion.":[110],"We":[111,153],"three":[114,185],"different":[115],"ways":[116],"apply":[118],"so-called":[125],"codes:":[127],"i)":[128],"Nonlinear":[129],"feature":[130,133],"normalization":[131],"space;":[134],"ii)":[135],"Direct":[136],"model":[137],"codes;":[144],"iii)":[145],"Joint":[146],"adaptive":[148],"with":[150],"codes.":[152],"evaluated":[155],"two":[161],"standard":[162],"tasks,":[165],"namely":[166],"TIMIT":[167],"phone":[168],"and":[170],"large":[171,192],"vocabulary":[172],"Switchboard":[177,206,242],"task.":[178],"Experimental":[179],"results":[180,207],"shown":[182,209],"that":[183,210],"all":[184],"quite":[188],"effective":[189],"adapt":[191],"models":[194],"using":[195,224,249],"only":[196,225],"small":[198],"amount":[199],"data.":[202],"For":[203],"example,":[204],"speaker-code-based":[213],"may":[216],"achieve":[217],"up":[218],"8-10%":[220],"relative":[221],"error":[222],"reduction":[223],"few":[227],"dozens":[228],"utterances":[231],"per":[232],"speaker.":[233],"Finally,":[234],"achieved":[237],"very":[238,255],"good":[239],"performance":[240,260],"(12.1%":[243],"WER)":[245],"after":[246],"sequence":[250],"criterion,":[252],"close":[256],"best":[259],"reported":[261],"task":[264],"(\u201cDeep":[265],"convolutional":[266],"LVCSR,\u201d":[270],"T.":[271],"N.":[272],"Sainath":[273],",":[274],"Proc.":[275],"IEEE":[276],"Acoust.,":[277],"Speech,":[278],"Signal":[279],"Process.,":[280],"2013).":[281]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":1}],"updated_date":"2026-02-19T06:27:42.648592","created_date":"2025-10-10T00:00:00"}