{"id":"https://openalex.org/W2090320273","doi":"https://doi.org/10.1109/icassp.2014.6854824","title":"Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code","display_name":"Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2090320273","doi":"https://doi.org/10.1109/icassp.2014.6854824","mag":"2090320273"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/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","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. 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":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. 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","Dept. of Electr. Eng. & Comput. Sci., York Univ., 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":"Dept. of Electr. Eng. & Comput. Sci., York Univ., Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"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","Dept. of Electr. Eng. & Comput. Sci., York Univ., 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":"Dept. of Electr. Eng. & Comput. Sci., York Univ., Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","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","Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. 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":"Nat. Eng. Lab. of Speech & Language Inf. Process., Univ. of Sci. & Technol. 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":null,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6339","last_page":"6343"},"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":0.9986000061035156,"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":0.9915000200271606,"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":0.8289135098457336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7681207060813904},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.727098286151886},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7017498016357422},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6497372388839722},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.518800675868988},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4755411148071289},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4725101888179779},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4591575860977173},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4527384042739868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4378955662250519},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42929500341415405},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42578592896461487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189680516719818},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2879680097103119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289135098457336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7681207060813904},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.727098286151886},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7017498016357422},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6497372388839722},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.518800675868988},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4755411148071289},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4725101888179779},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4591575860977173},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4527384042739868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4378955662250519},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42929500341415405},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42578592896461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189680516719818},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2879680097103119},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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.2014.6854824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1513862252","https://openalex.org/W1901264808","https://openalex.org/W1987238397","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W1993882792","https://openalex.org/W1998656041","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2012257340","https://openalex.org/W2016084804","https://openalex.org/W2046899276","https://openalex.org/W2052248915","https://openalex.org/W2063689849","https://openalex.org/W2077804127","https://openalex.org/W2080005694","https://openalex.org/W2081884280","https://openalex.org/W2100969003","https://openalex.org/W2112021726","https://openalex.org/W2117824967","https://openalex.org/W2121981798","https://openalex.org/W2146871184","https://openalex.org/W2156692643","https://openalex.org/W2397860787","https://openalex.org/W2403731734"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W4245698648","https://openalex.org/W2125642021","https://openalex.org/W4310979479"],"abstract_inverted_index":{"Recently":[0],"an":[1,59],"effective":[2,157],"fast":[3],"speaker":[4,9,47,67,204],"adaptation":[5,25,36,62,122,135,153,201,218],"method":[6,26,102,136,154,179,225],"using":[7,49,194],"discriminative":[8],"code":[10],"(SC)":[11],"has":[12,174],"been":[13],"proposed":[14,101,132,150,178],"for":[15,39,106,160,166,217],"the":[16,50,73,100,115,131,138,149,177,212,224],"hybrid":[17],"DNN-HMM":[18],"models":[19,76],"in":[20,63,137,187,191,226],"speech":[21,109],"recognition":[22,110,162],"[1].":[23,227],"This":[24],"depends":[27],"on":[28],"a":[29,33,78,98,196,208],"joint":[30],"learning":[31],"of":[32,80,94,200],"large":[34,107,139,168],"generic":[35],"neural":[37,123],"network":[38],"all":[40,91],"speakers":[41],"as":[42,44],"well":[43],"multiple":[45],"small":[46,161,198],"codes":[48,68],"standard":[51],"back-propagation":[52],"algorithm.":[53],"In":[54,125],"this":[55,126],"paper,":[56],"we":[57,128],"propose":[58],"alternative":[60],"direct":[61,133],"model":[64],"space,":[65],"where":[66],"are":[69],"directly":[70],"connected":[71],"to":[72,119,181,183,207],"original":[74],"DNN":[75],"through":[77],"set":[79],"new":[81],"connection":[82],"weights,":[83],"which":[84],"can":[85],"be":[86],"estimated":[87],"very":[88,156,167,197],"efficiently":[89],"from":[90,223],"or":[92],"part":[93],"training":[95,117,214],"data.":[96],"As":[97],"result,":[99],"is":[103,155,219],"more":[104],"suitable":[105],"scale":[108,140,169],"tasks":[111,163],"since":[112],"it":[113,173],"eliminates":[114],"time-consuming":[116],"process":[118],"estimate":[120],"another":[121],"networks.":[124],"work,":[127],"have":[129,146],"evaluated":[130],"SC-based":[134,151],"320-hr":[141],"Switchboard":[142,192],"task.":[143],"Experimental":[144],"results":[145],"shown":[147,175],"that":[148,176],"rapid":[152],"not":[158],"only":[159,195],"but":[164],"also":[165,220],"tasks.":[170],"For":[171],"example,":[172],"leads":[180],"up":[182],"8%":[184],"relative":[185],"reduction":[186],"word":[188],"error":[189],"rate":[190],"by":[193],"number":[199],"utterances":[202],"per":[203],"(from":[205],"10":[206],"few":[209],"dozens).":[210],"Moreover,":[211],"extra":[213],"time":[215],"required":[216],"significantly":[221],"reduced":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}