{"id":"https://openalex.org/W567546468","doi":"https://doi.org/10.21437/interspeech.2014-490","title":"Towards speaker adaptive training of deep neural network acoustic models","display_name":"Towards speaker adaptive training of deep neural network acoustic models","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W567546468","doi":"https://doi.org/10.21437/interspeech.2014-490","mag":"567546468"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Towards_Speaker_Adaptive_Training_of_Deep_Neural_Network_Acoustic_Models/6473777","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":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396872","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2058-7123"},"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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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":12.1995,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.99196414,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2189","last_page":"2193"},"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":0.9972000122070312,"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":0.7472688555717468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7253000736236572},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.710167407989502},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6142561435699463},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.559883713722229},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.509023904800415},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4939478039741516},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48296919465065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46805280447006226},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44079670310020447},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.4273649752140045},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4254574477672577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37719985842704773},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3289242386817932},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.061205387115478516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472688555717468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7253000736236572},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.710167407989502},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6142561435699463},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.559883713722229},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.509023904800415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4939478039741516},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48296919465065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46805280447006226},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44079670310020447},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.4273649752140045},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4254574477672577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37719985842704773},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3289242386817932},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.061205387115478516},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.21437/interspeech.2014-490","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1068","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1068&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473777","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:10.1.1.709.1428","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.1428","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/improve_sat_dnn.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.880.58","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.880.58","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repository.cmu.edu/cgi/viewcontent.cgi?article%3D1062%26context%3Dlti","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473777","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Towards_Speaker_Adaptive_Training_of_Deep_Neural_Network_Acoustic_Models/6473777","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/r1/6473777.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473777.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473777","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Towards_Speaker_Adaptive_Training_of_Deep_Neural_Network_Acoustic_Models/6473777","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":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W17156489","https://openalex.org/W82936479","https://openalex.org/W111477576","https://openalex.org/W159523117","https://openalex.org/W587565084","https://openalex.org/W619799124","https://openalex.org/W655723668","https://openalex.org/W1524333225","https://openalex.org/W1661756259","https://openalex.org/W1970088388","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2036351241","https://openalex.org/W2076828475","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2089917322","https://openalex.org/W2112739286","https://openalex.org/W2122272452","https://openalex.org/W2125610823","https://openalex.org/W2131342762","https://openalex.org/W2136879537","https://openalex.org/W2145094598","https://openalex.org/W2146635662","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2155273149","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2295119550","https://openalex.org/W2394932179","https://openalex.org/W2397534874","https://openalex.org/W2397860787","https://openalex.org/W2403731734","https://openalex.org/W2404921859","https://openalex.org/W2962719052","https://openalex.org/W2997574889"],"related_works":["https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835","https://openalex.org/W151018310","https://openalex.org/W3081187864"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,10,79,83,98,101,122],"concept":[3],"of":[4,12,24,45],"speaker":[5,26,58],"adaptive":[6],"training":[7],"(SAT)":[8],"in":[9,30,82],"context":[11],"deep":[13],"neural":[14,48],"network":[15],"(DNN)":[16],"acoustic":[17],"models.":[18],"Previous":[19],"studies":[20],"have":[21],"shown":[22],"success":[23],"performing":[25],"adaptation":[27],"for":[28],"DNNs":[29,40],"speech":[31],"recognition.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"apply":[37],"SAT":[38,73],"to":[39],"by":[41,77,134],"learning":[42],"two":[43],"types":[44],"feature":[46,85],"mapping":[47],"networks.":[49],"Given":[50],"an":[51],"initial":[52],"DNN":[53,65,81,111],"model,":[54],"these":[55],"networks":[56],"take":[57],"i-vectors":[59],"as":[60],"additional":[61],"information":[62],"and":[63,106,115],"project":[64],"inputs":[66,112],"into":[67],"a":[68,89],"speaker-normalized":[69],"space.":[70,86],"The":[71],"final":[72],"model":[74,103],"is":[75],"obtained":[76],"updating":[78],"canonical":[80],"normalized":[84],"Experiments":[87],"on":[88,121],"Switchboard":[90],"110-":[91],"hour":[92],"setup":[93],"show":[94],"that":[95],"compared":[96],"with":[97],"baseline":[99],"DNN,":[100],"SAT-DNN":[102],"brings":[104],"7.5%":[105],"6.0%":[107],"relative":[108],"improvement":[109],"when":[110],"are":[113],"speaker-independent":[114],"speakeradapted":[116],"features":[117],"respectively.":[118],"Further":[119],"evaluations":[120],"more":[123],"challenging":[124],"BABEL":[125],"datasets":[126],"reveal":[127],"significant":[128],"word":[129],"error":[130],"rate":[131],"reduction":[132],"achieved":[133],"SAT-DNN.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}