{"id":"https://openalex.org/W2048526313","doi":"https://doi.org/10.1109/taslp.2015.2457612","title":"Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors","display_name":"Speaker Adaptive Training of Deep Neural Network Acoustic Models Using I-Vectors","publication_year":2015,"publication_date":"2015-07-16","ids":{"openalex":"https://openalex.org/W2048526313","doi":"https://doi.org/10.1109/taslp.2015.2457612","mag":"2048526313"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2457612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2457612","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396885","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2928-2692"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, Pttsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":20.517,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.9937748,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"23","issue":"11","first_page":"1938","last_page":"1949"},"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":0.9976000189781189,"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":0.9962999820709229,"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":0.7220784425735474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6167058944702148},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5660400986671448},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5591193437576294},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5474584102630615},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.5415914058685303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5353620052337646},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5302490592002869},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5011870861053467},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4683014452457428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4271283447742462},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4169424772262573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37203699350357056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220784425735474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6167058944702148},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5660400986671448},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5591193437576294},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5474584102630615},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.5415914058685303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5353620052337646},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5302490592002869},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5011870861053467},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4683014452457428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271283447742462},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4169424772262573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37203699350357056},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2457612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2457612","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":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W82936479","https://openalex.org/W111477576","https://openalex.org/W567546468","https://openalex.org/W587565084","https://openalex.org/W1524333225","https://openalex.org/W1599512239","https://openalex.org/W1661756259","https://openalex.org/W1722135069","https://openalex.org/W1970088388","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W1995562189","https://openalex.org/W2002342963","https://openalex.org/W2015633636","https://openalex.org/W2028706510","https://openalex.org/W2033256038","https://openalex.org/W2033310064","https://openalex.org/W2036351241","https://openalex.org/W2039057510","https://openalex.org/W2045317385","https://openalex.org/W2056445351","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2094147890","https://openalex.org/W2112021726","https://openalex.org/W2112739286","https://openalex.org/W2117239706","https://openalex.org/W2122272452","https://openalex.org/W2136879537","https://openalex.org/W2143612262","https://openalex.org/W2145094598","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2187166234","https://openalex.org/W2213952365","https://openalex.org/W2250357346","https://openalex.org/W2290318471","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2295119550","https://openalex.org/W2296748324","https://openalex.org/W2397534874","https://openalex.org/W2403307129","https://openalex.org/W2403524927","https://openalex.org/W2403731734","https://openalex.org/W2997574889","https://openalex.org/W6603403951","https://openalex.org/W6604441197","https://openalex.org/W6615969787","https://openalex.org/W6617215739","https://openalex.org/W6631362777","https://openalex.org/W6636969168","https://openalex.org/W6637565935","https://openalex.org/W6681096077","https://openalex.org/W6687050748","https://openalex.org/W6688428952","https://openalex.org/W6691509046","https://openalex.org/W6696830301","https://openalex.org/W6696934422","https://openalex.org/W6696982659","https://openalex.org/W6697090674","https://openalex.org/W6697318756","https://openalex.org/W6712029055","https://openalex.org/W6713292810","https://openalex.org/W6713701104"],"related_works":["https://openalex.org/W2546942002","https://openalex.org/W2970216048","https://openalex.org/W2382607599","https://openalex.org/W2060018656","https://openalex.org/W2125776881","https://openalex.org/W2508937276","https://openalex.org/W2736005052","https://openalex.org/W4244902868","https://openalex.org/W1971793356","https://openalex.org/W2039057510"],"abstract_inverted_index":{"In":[0,105],"acoustic":[1,129],"modeling,":[2],"speaker":[3,61],"adaptive":[4,75],"training":[5,27,176],"(SAT)":[6],"has":[7],"been":[8],"a":[9,50,84,100,162,184],"long-standing":[10],"technique":[11],"for":[12,56,127,220],"the":[13,39,122,140,173,188,229],"traditional":[14],"Gaussian":[15],"mixture":[16],"models":[17,20,76,115],"(GMMs).":[18],"Acoustic":[19],"trained":[21],"with":[22,183,204],"SAT":[23,42,55,103],"become":[24],"independent":[25],"of":[26,41,125,160,175],"speakers":[28],"and":[29,48,96,117,139,150,193,203],"generalize":[30],"better":[31],"to":[32,43,52,70,92,112,147,157,171],"unseen":[33],"testing":[34,230],"speakers.":[35],"This":[36,87],"paper":[37],"ports":[38],"idea":[40],"deep":[44],"neural":[45,68],"networks":[46],"(DNNs),":[47],"proposes":[49],"framework":[51,64,88],"perform":[53],"feature-space":[54],"DNNs.":[57],"Using":[58],"i-vectors":[59],"as":[60],"representations,":[62],"our":[63],"learns":[65],"an":[66],"adaptation":[67,143,153,206],"network":[69,97],"derive":[71],"speaker-normalized":[72],"features.":[73],"Speaker":[74],"are":[77],"obtained":[78],"by":[79],"fine-tuning":[80],"DNNs":[81],"in":[82,216],"such":[83],"feature":[85,94],"space.":[86],"can":[89],"be":[90],"applied":[91,207],"various":[93],"types":[95],"structures,":[98],"posing":[99],"very":[101],"general":[102],"solution.":[104],"this":[106],"paper,":[107],"we":[108,120,145],"fully":[109],"investigate":[110],"how":[111],"build":[113],"SAT-DNN":[114,189,221],"effectively":[116],"efficiently.":[118],"First,":[119],"study":[121],"optimal":[123],"configurations":[124],"SAT-DNNs":[126,138,149],"large-scale":[128],"modeling":[130],"tasks.":[131],"Then,":[132],"after":[133],"presenting":[134],"detailed":[135],"comparisons":[136],"between":[137],"existing":[141],"DNN":[142,152,186],"methods,":[144],"propose":[146],"combine":[148],"model-space":[151,205],"during":[154],"decoding.":[155],"Finally,":[156],"accelerate":[158],"learning":[159],"SAT-DNNs,":[161],"simple":[163],"yet":[164],"effective":[165],"strategy,":[166],"frame":[167,213],"skipping,":[168],"is":[169],"employed":[170],"reduce":[172],"size":[174],"data.":[177,231],"Our":[178],"experiments":[179],"show":[180],"that":[181],"compared":[182],"strong":[185],"baseline,":[187],"model":[190],"achieves":[191],"13.5%":[192],"17.5%":[194],"relative":[195],"improvement":[196],"on":[197,212,228],"word":[198],"error":[199],"rates":[200],"(WERs),":[201],"without":[202],"respectively.":[208],"Data":[209],"reduction":[210],"based":[211],"skipping":[214],"results":[215],"2":[217],"\u00d7":[218],"speed-up":[219],"training,":[222],"while":[223],"causing":[224],"negligible":[225],"WER":[226],"loss":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}