{"id":"https://openalex.org/W1722135069","doi":"https://doi.org/10.21437/interspeech.2010-221","title":"On speaker adaptive training of artificial neural networks","display_name":"On speaker adaptive training of artificial neural networks","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1722135069","doi":"https://doi.org/10.21437/interspeech.2010-221","mag":"1722135069"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-221","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11025/16965","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032353277","display_name":"Jan Trmal","orcid":null},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jan Trmal","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105688684","display_name":"Jan Zelinka","orcid":null},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Zelinka","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017114383","display_name":"Lud\u011bk M\u00fcller","orcid":"https://orcid.org/0000-0002-6581-6348"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lud\u011bk M\u00fcller","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032353277"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":null,"apc_paid":null,"fwci":1.3965,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83897554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"554","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9937999844551086,"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":0.9708999991416931,"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":0.7879775762557983},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7852720618247986},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7776221036911011},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7180075645446777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6560488939285278},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6181149482727051},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6046873331069946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5663918852806091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5606635212898254},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5494375824928284},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4667753279209137},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.45090949535369873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879775762557983},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7852720618247986},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7776221036911011},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7180075645446777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6560488939285278},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6181149482727051},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6046873331069946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5663918852806091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5606635212898254},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5494375824928284},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4667753279209137},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.45090949535369873},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-221","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace5.zcu.cz:11025/16965","is_oa":true,"landing_page_url":"http://www.kky.zcu.cz/cs/publications/TrmalJan_2010_OnSpeakerAdaptive","pdf_url":"http://hdl.handle.net/11025/16965","source":{"id":"https://openalex.org/S4306400586","display_name":"Digital Library (University of West Bohemia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92715842","host_organization_name":"University of West Bohemia in Pilsen","host_organization_lineage":["https://openalex.org/I92715842"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"\u010dl\u00e1nek"}],"best_oa_location":{"id":"pmh:oai:dspace5.zcu.cz:11025/16965","is_oa":true,"landing_page_url":"http://www.kky.zcu.cz/cs/publications/TrmalJan_2010_OnSpeakerAdaptive","pdf_url":"http://hdl.handle.net/11025/16965","source":{"id":"https://openalex.org/S4306400586","display_name":"Digital Library (University of West Bohemia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92715842","host_organization_name":"University of West Bohemia in Pilsen","host_organization_lineage":["https://openalex.org/I92715842"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"\u010dl\u00e1nek"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1722135069.pdf","grobid_xml":"https://content.openalex.org/works/W1722135069.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W162588823","https://openalex.org/W1507177964","https://openalex.org/W1554663460","https://openalex.org/W1555754712","https://openalex.org/W2164931619","https://openalex.org/W2167763959","https://openalex.org/W2407126428","https://openalex.org/W3141839452"],"related_works":["https://openalex.org/W1992908141","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W4255044973","https://openalex.org/W2499802997"],"abstract_inverted_index":{"In":[0,51],"the":[1,8,28,35,52,58,81,88,93,129],"paper":[2],"we":[3,56,66],"present":[4],"two":[5,100],"techniques":[6],"improving":[7],"recognition":[9,42],"accuracy":[10],"of":[11,20,27,117,135],"multilayer":[12],"perceptron":[13],"neural":[14],"networks":[15],"(MLP":[16],"ANN)":[17],"by":[18],"means":[19],"adopting":[21],"Speaker":[22],"Adaptive":[23],"Training.":[24],"The":[25,108],"use":[26],"MLP":[29,120],"ANN,":[30],"usually":[31],"in":[32,40,111],"combination":[33],"with":[34,85],"TRAPS":[36],"parametrization,":[37],"includes":[38],"applications":[39],"speech":[41,105],"tasks,":[43],"discriminative":[44],"features":[45],"production":[46],"for":[47],"GMM-HMM":[48],"and":[49,126],"other.":[50],"first":[53],"SAT":[54,118],"experiments,":[55],"used":[57],"VTLN":[59],"as":[60],"a":[61,68],"speaker":[62,70],"normalization":[63,71],"technique.":[64],"Moreover,":[65],"developed":[67],"novel":[69],"technique":[72],"called":[73],"Minimum":[74],"Error":[75],"Linear":[76],"Transform":[77],"(MELT)":[78],"that":[79,115],"resembles":[80],"cMLLR/fMLLR":[82],"method":[83],"\\\\cite{gales96variance}":[84],"respect":[86],"to":[87,132],"possible":[89],"application":[90],"either":[91],"on":[92,103,128],"model":[94],"or":[95],"features.":[96],"We":[97],"tested":[98],"these":[99,112],"methods":[101],"extensively":[102],"telephone":[104],"corpus":[106],"SpeechDat-East.":[107],"results":[109],"obtained":[110],"experiments":[113],"suggest":[114],"incorporation":[116],"into":[119],"ANN":[121],"training":[122],"process":[123],"is":[124],"beneficial":[125],"depending":[127],"setup":[130],"leads":[131],"significant":[133],"decrease":[134],"phoneme":[136],"error":[137],"rate":[138],"(3%":[139],"--":[140,144],"8%":[141],"absolute,":[142],"12%":[143],"25%":[145],"relative).":[146]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
