{"id":"https://openalex.org/W3011773325","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023185","title":"Batch Normalization based Unsupervised Speaker Adaptation for Acoustic Models","display_name":"Batch Normalization based Unsupervised Speaker Adaptation for Acoustic Models","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011773325","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023185","mag":"3011773325"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078525423"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20620083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9939000010490417,"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/normalization","display_name":"Normalization (sociology)","score":0.9288347959518433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766964852809906},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6224644780158997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.591549277305603},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5895580649375916},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5375001430511475},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5355315804481506},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5198215246200562},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5167105197906494},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4824974536895752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46848830580711365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4509909451007843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12038111686706543}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9288347959518433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766964852809906},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6224644780158997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.591549277305603},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5895580649375916},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5375001430511475},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5355315804481506},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5198215246200562},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5167105197906494},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4824974536895752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46848830580711365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4509909451007843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12038111686706543},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2112021726","https://openalex.org/W2134167844","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2398054607","https://openalex.org/W2515119768","https://openalex.org/W2519224033","https://openalex.org/W2530876040","https://openalex.org/W2641129314","https://openalex.org/W2697254725","https://openalex.org/W2939164678","https://openalex.org/W2939173691","https://openalex.org/W2963217176","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6676587989"],"related_works":["https://openalex.org/W203970584","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W4297779039","https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W4401751953","https://openalex.org/W156567445","https://openalex.org/W3136989387","https://openalex.org/W4287266619"],"abstract_inverted_index":{"This":[0,58],"paper":[1],"proposes":[2],"a":[3],"simple":[4],"yet":[5],"effective":[6],"unsupervised":[7],"speaker":[8],"adaptation":[9,83,115,119],"approach":[10,25,59],"for":[11,41],"batch":[12,34],"normalization":[13,35],"based":[14],"deep":[15],"neural":[16],"network":[17],"acoustic":[18,69],"models.":[19],"The":[20,77],"basic":[21],"idea":[22],"of":[23,47,67],"this":[24],"is":[26],"to":[27,54,62],"recompute":[28],"means":[29],"and":[30,106],"variances":[31],"in":[32],"all":[33],"layers":[36],"over":[37],"the":[38,45,48,55,68,81,87,104,117],"test":[39,49,89],"data":[40,50],"every":[42],"speaker.":[43],"Thus":[44],"distribution":[46],"can":[51],"be":[52],"close":[53],"training":[56],"data.":[57],"doesn't":[60],"need":[61],"adjust":[63],"any":[64],"trainable":[65],"parameters":[66],"model.":[70],"Experiments":[71],"are":[72],"conducted":[73],"on":[74,86],"CHiME-3":[75],"datasets.":[76],"results":[78],"show":[79],"that":[80],"proposed":[82,113],"obtains":[84,120],"improvement":[85],"real":[88],"set":[90],"by":[91],"2.17":[92],"%":[93],"relative":[94],"average":[95],"word":[96],"error":[97],"rate":[98],"(WER)":[99],"reduction":[100],"when":[101],"compared":[102],"with":[103,116],"scaling":[105],"shifting":[107],"factors":[108],"(SSF)":[109],"adaptation.":[110],"Combining":[111],"our":[112],"MV":[114],"SSF":[118],"further":[121],"improvement.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}