{"id":"https://openalex.org/W3008391164","doi":"https://doi.org/10.1109/asru46091.2019.9003883","title":"Online Batch Normalization Adaptation for Automatic Speech Recognition","display_name":"Online Batch Normalization Adaptation for Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008391164","doi":"https://doi.org/10.1109/asru46091.2019.9003883","mag":"3008391164"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003883","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":["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/A5048085326","display_name":"Franco Mana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127533","display_name":"Nuance Communications (Italy)","ror":"https://ror.org/038333j82","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210127533"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Mana","raw_affiliation_strings":["Nuance Communications, Inc., Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Torino, Italy","institution_ids":["https://openalex.org/I4210127533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications, Inc., Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056510268","display_name":"Roberto Gemello","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127533","display_name":"Nuance Communications (Italy)","ror":"https://ror.org/038333j82","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210127533"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Gemello","raw_affiliation_strings":["Nuance Communications, Inc., Torino, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Torino, Italy","institution_ids":["https://openalex.org/I4210127533"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications, Inc., Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"875","last_page":"880"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9991000294685364,"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":0.8352432250976562},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8342286944389343},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6871873736381531},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6866738200187683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5622431635856628},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5567792057991028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502184629440308},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5470827221870422},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5370667576789856},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5238780379295349},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4938107430934906},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.4433669447898865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352432250976562},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8342286944389343},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6871873736381531},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6866738200187683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5622431635856628},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5567792057991028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502184629440308},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5470827221870422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5370667576789856},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5238780379295349},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4938107430934906},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.4433669447898865},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003883","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1513862252","https://openalex.org/W1836465849","https://openalex.org/W1989549063","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2125964738","https://openalex.org/W2160306971","https://openalex.org/W2194775991","https://openalex.org/W2293634267","https://openalex.org/W2299668505","https://openalex.org/W2302255633","https://openalex.org/W2398187210","https://openalex.org/W2400607496","https://openalex.org/W2514740276","https://openalex.org/W2515863432","https://openalex.org/W2641129314","https://openalex.org/W2750499125","https://openalex.org/W2782451907","https://openalex.org/W2889055315","https://openalex.org/W2889163603","https://openalex.org/W2916979304","https://openalex.org/W2962824709","https://openalex.org/W2963113185","https://openalex.org/W2963266252","https://openalex.org/W2963596039","https://openalex.org/W2972799770","https://openalex.org/W6607333740","https://openalex.org/W6630673164","https://openalex.org/W6638667902","https://openalex.org/W6679053740","https://openalex.org/W6696934422","https://openalex.org/W6697673422","https://openalex.org/W6698183232","https://openalex.org/W6735593169","https://openalex.org/W6741386133","https://openalex.org/W6746892368","https://openalex.org/W6747836893","https://openalex.org/W6766137760"],"related_works":["https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W4287755480","https://openalex.org/W4324316636","https://openalex.org/W2970987681","https://openalex.org/W2898211994","https://openalex.org/W3042419602","https://openalex.org/W2966649771","https://openalex.org/W4285236786","https://openalex.org/W4226166052"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Network":[2],"(DNN)":[3],"acoustic":[4,123,151],"models":[5,124],"are":[6],"sensitive":[7],"to":[8,55,73,91,143,168],"the":[9,80,83,98,101,108,160,164,169],"mismatch":[10,148],"between":[11],"training":[12,145,171],"and":[13,51,107,138,146],"testing":[14,147],"environments.":[15],"When":[16],"a":[17,35,40,116,136,184],"trained":[18],"model":[19,170],"is":[20,52,89,154],"tested":[21],"on":[22,94],"unseen":[23],"speakers,":[24],"domain,":[25],"or":[26],"environment,":[27],"recognition":[28,48],"accuracy":[29,49,181],"can":[30,46,179],"degrade":[31],"substantially.":[32],"In":[33,131],"such":[34,61],"case,":[36],"offline":[37],"adaptation":[38,64,88,112,115,141,158],"with":[39,163],"fair":[41],"amount":[42,103],"of":[43,63,104,110,129,159],"field":[44],"data":[45,106],"improve":[47,180],"significantly,":[50],"commonly":[53],"applied":[54,167],"ASR":[56],"systems":[57],"in":[58,71,79,183],"practice.":[59],"Ideally,":[60],"kind":[62],"should":[65],"be":[66],"done":[67,155],"online":[68,87,114,140,157],"as":[69],"well":[70],"order":[72],"catch":[74],"any":[75],"unexpected":[76],"dynamic":[77],"changes":[78],"environments":[81],"during":[82],"inference":[84],"process.":[85,172],"However,":[86],"subject":[90],"strict":[92],"constraints":[93],"computational":[95],"cost.":[96],"On":[97],"other":[99],"hand,":[100],"small":[102],"available":[105],"nature":[109],"unsupervised":[111],"make":[113],"very":[117],"challenging":[118],"task,":[119],"especially":[120],"for":[121,149,188],"DNN":[122,150,190],"which":[125],"normally":[126],"contain":[127],"millions":[128],"parameters.":[130],"this":[132,177],"paper,":[133],"we":[134],"introduce":[135],"simple":[137],"effective":[139],"technique":[142,178],"compensate":[144],"models.":[152],"It":[153],"via":[156],"parameters":[161],"associated":[162],"batch":[165],"normalization":[166],"Our":[173],"results":[174],"show":[175],"that":[176],"significantly":[182],"domain":[185],"mismatched":[186],"scenario":[187],"different":[189],"architectures.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}