{"id":"https://openalex.org/W2045317385","doi":"https://doi.org/10.1109/slt.2014.7078568","title":"Improvements to speaker adaptive training of deep neural networks","display_name":"Improvements to speaker adaptive training of deep neural networks","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2045317385","doi":"https://doi.org/10.1109/slt.2014.7078568","mag":"2045317385"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Improvements_to_speaker_adaptive_training_of_deep_neural_networks/6473414","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090730336","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0003-0286-8439"},"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":"Lu Jiang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#","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","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#","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","Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science, Carnegie Mellon University, USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003251887"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":12.2384,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98629623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":null,"first_page":"165","last_page":"170"},"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":0.9990000128746033,"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":0.8080564141273499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6214834451675415},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6108622550964355},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5946553945541382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5892757773399353},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5593041181564331},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5413269400596619},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5359374284744263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5216888785362244},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5077491998672485},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4647345542907715},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4454251825809479},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42475077509880066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4133601188659668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080564141273499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6214834451675415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6108622550964355},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5946553945541382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892757773399353},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5593041181564331},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5413269400596619},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5359374284744263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5216888785362244},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5077491998672485},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4647345542907715},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4454251825809479},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42475077509880066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4133601188659668},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/slt.2014.7078568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1062","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1062&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473414","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.7205","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.7205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eymiao/pub/tasl_sat.pdf","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473414","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improvements_to_speaker_adaptive_training_of_deep_neural_networks/6473414","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473414.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473414.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473414","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improvements_to_speaker_adaptive_training_of_deep_neural_networks/6473414","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W111477576","https://openalex.org/W135040384","https://openalex.org/W567546468","https://openalex.org/W587565084","https://openalex.org/W619799124","https://openalex.org/W1524333225","https://openalex.org/W1661756259","https://openalex.org/W1970088388","https://openalex.org/W1993409002","https://openalex.org/W2025198378","https://openalex.org/W2033256038","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2092776130","https://openalex.org/W2112739286","https://openalex.org/W2121486117","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2295119550","https://openalex.org/W2296748324","https://openalex.org/W2397534874","https://openalex.org/W2397860787","https://openalex.org/W2404921859","https://openalex.org/W2793908218","https://openalex.org/W2962719052","https://openalex.org/W2997574889","https://openalex.org/W6615969787","https://openalex.org/W6617215739","https://openalex.org/W6619536949","https://openalex.org/W6631362777","https://openalex.org/W6636969168","https://openalex.org/W6681096077","https://openalex.org/W6697090674","https://openalex.org/W6712029055","https://openalex.org/W6712397180","https://openalex.org/W6713136263"],"related_works":["https://openalex.org/W2059299633","https://openalex.org/W2760085659","https://openalex.org/W2972074553","https://openalex.org/W2732542196","https://openalex.org/W2940977206","https://openalex.org/W2995914718","https://openalex.org/W2546942002","https://openalex.org/W3156786002","https://openalex.org/W2977314777","https://openalex.org/W4307883119"],"abstract_inverted_index":{"Speaker":[0],"adaptive":[1],"training":[2,67],"(SAT)":[3],"is":[4,76,131],"a":[5,120],"well":[6],"studied":[7],"technique":[8],"for":[9,21,98],"Gaussian":[10],"mixture":[11],"acoustic":[12,90],"models":[13,36],"(GMMs).":[14],"Recently":[15],"we":[16,48,59,102],"proposed":[17],"to":[18,52,63,78,133],"perform":[19],"SAT":[20],"deep":[22],"neural":[23,87],"networks":[24],"(DNNs),":[25],"with":[26,107],"speaker":[27,109],"i-vectors":[28],"applied":[29],"in":[30],"feature":[31,70,83,95],"learning.":[32],"The":[33],"resulting":[34],"SAT-DNN":[35,74],"significantly":[37],"outperform":[38],"DNNs":[39],"on":[40],"word":[41],"error":[42],"rates":[43],"(WERs).":[44],"In":[45],"this":[46],"paper,":[47],"present":[49],"different":[50],"methods":[51],"further":[53],"improve":[54,79],"and":[55,68,92],"extend":[56],"SAT-DNN.":[57,139],"First,":[58],"conduct":[60],"detailed":[61],"analysis":[62],"investigate":[64],"i-vector":[65,105],"extractor":[66],"flexible":[69],"fusion.":[71],"Second,":[72],"the":[73,104,127,135],"approach":[75],"extended":[77],"tasks":[80],"including":[81],"bottleneck":[82],"(BNF)":[84],"generation,":[85],"convolutional":[86],"network":[88],"(CNN)":[89],"modeling":[91],"multilingual":[93],"DNN-based":[94],"extraction.":[96],"Third,":[97],"transcribing":[99],"multimedia":[100],"data,":[101],"enrich":[103],"representation":[106],"global":[108],"attributes":[110],"(age,":[111],"gender,":[112],"etc.)":[113],"obtained":[114],"automatically":[115],"from":[116],"video":[117],"signals.":[118],"On":[119],"collection":[121],"of":[122,126,138],"instructional":[123],"videos,":[124],"incorporation":[125],"additional":[128],"visual":[129],"features":[130],"observed":[132],"boost":[134],"recognition":[136],"accuracy":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}