{"id":"https://openalex.org/W2976255838","doi":"https://doi.org/10.1109/asru46091.2019.9004028","title":"Embeddings for DNN Speaker Adaptive Training","display_name":"Embeddings for DNN Speaker Adaptive Training","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2976255838","doi":"https://doi.org/10.1109/asru46091.2019.9004028","mag":"2976255838"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004028","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.13537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026578899","display_name":"Joanna Rownicka","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joanna Rownicka","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technology Research, University of Edinburgh UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technology Research, University of Edinburgh UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","Centre for Speech Technology Research, University of Edinburgh UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987999796867371,"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":0.9983999729156494,"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":0.7579548358917236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7048380970954895},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.669983983039856},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5630438923835754},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5429738163948059},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.480411559343338},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.470766544342041},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4470067024230957},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4467337131500244},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4438864290714264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43284448981285095},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4326581358909607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4318464696407318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579548358917236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7048380970954895},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.669983983039856},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5630438923835754},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5429738163948059},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.480411559343338},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.470766544342041},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4470067024230957},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4467337131500244},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4438864290714264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43284448981285095},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4326581358909607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4318464696407318},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/asru46091.2019.9004028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004028","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.13537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.13537","pdf_url":"https://arxiv.org/pdf/1909.13537","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2976255838","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1909.13537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d4e9f343-eb92-4daf-8dd5-0ad7cf15fbb5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d4e9f343-eb92-4daf-8dd5-0ad7cf15fbb5","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R\u00f3wnicka, J, Bell, P & Renals, S 2020, Embeddings for DNN speaker adaptive training. in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 479-486, IEEE Automatic Speech Recognition and Understanding Workshop 2019, Sentosa, Singapore, 14/12/19. https://doi.org/10.1109/ASRU46091.2019.9004028","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d4e9f343-eb92-4daf-8dd5-0ad7cf15fbb5","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/9004028","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R\u00f3wnicka, J, Bell, P & Renals, S 2020, Embeddings for DNN speaker adaptive training. in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Institute of Electrical and Electronics Engineers, pp. 479-486, IEEE Automatic Speech Recognition and Understanding Workshop 2019, Sentosa, Singapore, 14/12/19. https://doi.org/10.1109/ASRU46091.2019.9004028","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1909.13537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1909.13537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.13537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.13537","pdf_url":"https://arxiv.org/pdf/1909.13537","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"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":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1592672653","https://openalex.org/W2048526313","https://openalex.org/W2079623482","https://openalex.org/W2153773386","https://openalex.org/W2237224976","https://openalex.org/W2239847623","https://openalex.org/W2398776621","https://openalex.org/W2404568753","https://openalex.org/W2404901536","https://openalex.org/W2514740276","https://openalex.org/W2746742816","https://openalex.org/W2766901645","https://openalex.org/W2786152338","https://openalex.org/W2799674897","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2900200882","https://openalex.org/W2938374794","https://openalex.org/W2962835968","https://openalex.org/W2963381607","https://openalex.org/W2963596039","https://openalex.org/W2964227577","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6690441418","https://openalex.org/W6713570806","https://openalex.org/W6713726233","https://openalex.org/W6737563559","https://openalex.org/W6741386133","https://openalex.org/W6743352670"],"related_works":["https://openalex.org/W3007327651","https://openalex.org/W1487851247","https://openalex.org/W2890964092","https://openalex.org/W2401144871","https://openalex.org/W2401822949","https://openalex.org/W2612434969","https://openalex.org/W2951534110","https://openalex.org/W2889793054","https://openalex.org/W2963918434","https://openalex.org/W2055842011","https://openalex.org/W2798824629","https://openalex.org/W2398054607","https://openalex.org/W2395596777","https://openalex.org/W2939762919","https://openalex.org/W3016021376","https://openalex.org/W2796339975","https://openalex.org/W2582930187","https://openalex.org/W3048784519","https://openalex.org/W2173092938","https://openalex.org/W2408125366"],"abstract_inverted_index":{"In":[0,92],"this":[1],"work,":[2,98],"we":[3,99],"investigate":[4,50],"the":[5,43,47,85,89,93,130,159,164],"use":[6],"of":[7,12,20,46,96,135,163,177],"embeddings":[8,86],"for":[9,126,132,166],"speaker-adaptive":[10],"training":[11,63],"DNNs":[13],"(DNN-SAT)":[14],"focusing":[15],"on":[16,84],"a":[17,31,61,65,79,136,191],"small":[18],"amount":[19],"adaptation":[21,67],"data":[22],"per":[23],"speaker.":[24],"DNN-SAT":[25,168],"can":[26],"be":[27],"viewed":[28],"as":[29],"learning":[30],"mapping":[32],"from":[33],"each":[34],"embedding":[35,125],"to":[36,42,53,70,87,117,149],"transformation":[37],"parameters":[38,45],"that":[39,59],"are":[40],"applied":[41,69],"shared":[44],"DNN.":[48],"We":[49,128],"different":[51,101],"approaches":[52],"applying":[54],"these":[55],"transformations,":[56],"and":[57,105,179,190],"find":[58,129],"with":[60,142],"good":[62],"strategy,":[64],"multi-layer":[66],"network":[68],"all":[71],"hidden":[72],"layers":[73],"is":[74,139],"no":[75],"more":[76,151],"effective":[77],"than":[78,154],"single":[80],"linear":[81],"layer":[82],"acting":[83],"transform":[88],"input":[90],"features.":[91],"second":[94],"part":[95],"our":[97],"evaluate":[100],"embed-dings":[102,165],"(i-vectors,":[103],"x-vectors":[104],"deep":[106],"CNN":[107],"embeddings)":[108],"in":[109,115,146],"an":[110,124],"additional":[111],"speaker":[112,133,156],"recognition":[113,134],"task":[114],"order":[116],"gain":[118],"insight":[119],"into":[120],"what":[121],"should":[122],"characterize":[123],"DNN-SAT.":[127],"performance":[131],"given":[137],"representation":[138],"not":[140],"correlated":[141],"its":[143],"ASR":[144],"performance;":[145],"fact,":[147],"ability":[148],"capture":[150],"speech":[152],"attributes":[153],"just":[155],"identity":[157],"was":[158],"most":[160],"important":[161],"characteristic":[162],"efficient":[167],"ASR.":[169],"Our":[170],"best":[171],"models":[172],"achieved":[173],"relative":[174],"WER":[175],"gains":[176],"4%":[178],"9%":[180],"over":[181],"DNN":[182],"baselines":[183],"using":[184],"speaker-level":[185],"cepstral":[186],"mean":[187],"normalisation":[188],"(CMN),":[189],"fully":[192],"speaker-independent":[193],"model,":[194],"respectively.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}