{"id":"https://openalex.org/W2794588495","doi":"https://doi.org/10.21437/interspeech.2018-1897","title":"Empirical Evaluation of Speaker Adaptation on DNN Based Acoustic Model","display_name":"Empirical Evaluation of Speaker Adaptation on DNN Based Acoustic Model","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2794588495","doi":"https://doi.org/10.21437/interspeech.2018-1897","mag":"2794588495"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1897","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.10146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036269989","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0001-8941-723X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Xiaomi, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Xiaomi, Beijing, China","Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2429","last_page":"2433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9925000071525574,"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":0.9902999997138977,"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":0.7981995344161987},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7686914801597595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7649346590042114},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6584441065788269},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6004807949066162},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5770906805992126},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.44924822449684143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3880261480808258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06252977252006531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981995344161987},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7686914801597595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7649346590042114},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6584441065788269},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6004807949066162},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5770906805992126},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.44924822449684143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3880261480808258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06252977252006531},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1897","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.10146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10146","pdf_url":"https://arxiv.org/pdf/1803.10146","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.10146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10146","pdf_url":"https://arxiv.org/pdf/1803.10146","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W26405188","https://openalex.org/W70088150","https://openalex.org/W82936479","https://openalex.org/W1489125746","https://openalex.org/W1499864241","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2048526313","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2094147890","https://openalex.org/W2100969003","https://openalex.org/W2121981798","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2165108269","https://openalex.org/W2188183693","https://openalex.org/W2208299922","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2519224033","https://openalex.org/W2542851870","https://openalex.org/W2916979304","https://openalex.org/W2916986993","https://openalex.org/W2963217176","https://openalex.org/W2963920996","https://openalex.org/W2964084166"],"related_works":["https://openalex.org/W2031478549","https://openalex.org/W3048205211","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"Speaker":[0,138],"adaptation":[1,34,85,97,139],"aims":[2],"to":[3,15,72],"estimate":[4],"a":[5,11,102],"speaker":[6,12,27,84,121,126],"specific":[7],"acoustic":[8,61,105],"model":[9,122],"from":[10,26],"independent":[13],"one":[14],"minimize":[16],"the":[17,20,45,110,130],"mismatch":[18],"between":[19,55],"training":[21],"and":[22,89,112,123,135],"testing":[23],"conditions":[24],"arisen":[25],"variabilities.":[28],"A":[29],"variety":[30],"of":[31,81,96,132],"neural":[32],"network":[33],"methods":[35,134],"have":[36,43,63],"been":[37,64],"proposed":[38],"since":[39],"deep":[40],"learning":[41],"models":[42,62],"become":[44],"main":[46],"stream.":[47],"But":[48],"there":[49],"still":[50],"lacks":[51],"an":[52,78],"experimental":[53],"comparison":[54],"different":[56,94,133],"methods,":[57],"especially":[58],"when":[59],"DNN-based":[60],"advanced":[65],"greatly.":[66],"In":[67],"this":[68,74],"paper,":[69],"we":[70,114],"aim":[71],"close":[73],"gap":[75],"by":[76,144],"providing":[77],"empirical":[79],"evaluation":[80],"three":[82],"typical":[83],"methods:":[86],"LIN,":[87],"LHUC":[88],"KLD.":[90],"Adaptation":[91],"experiments,":[92],"with":[93,117],"size":[95],"data,":[98],"are":[99,115,118],"conducted":[100],"on":[101],"strong":[103],"TDNN-LSTM":[104],"model.":[106,127],"More":[107],"challengingly,":[108],"here,":[109],"source":[111],"target":[113],"concerned":[116],"standard":[119],"Mandarin":[120,125],"accented":[124],"We":[128],"compare":[129],"performances":[131],"their":[136],"combinations.":[137],"performance":[140],"is":[141],"also":[142],"examined":[143],"speaker's":[145],"accent":[146],"degree.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}