{"id":"https://openalex.org/W3202106304","doi":"https://doi.org/10.1109/asru51503.2021.9688142","title":"Parameterized Channel Normalization for Far-Field Deep Speaker Verification","display_name":"Parameterized Channel Normalization for Far-Field Deep Speaker Verification","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3202106304","doi":"https://doi.org/10.1109/asru51503.2021.9688142","mag":"3202106304"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688142","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5014303571","display_name":"Xuechen Liu","orcid":"https://orcid.org/0000-0003-1207-5651"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["School of Computing, University of Eastern Finland,Joensuu,Finland","School of Computing, University of Eastern Finland, Joensuu, Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland,Joensuu,Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Md Sahidullah","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria, LORIA,Nancy,France,F-54000","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland,Joensuu,Finland","School of Computing, University of Eastern Finland, Joensuu, Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland,Joensuu,Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014303571"],"corresponding_institution_ids":["https://openalex.org/I175532246"],"apc_list":null,"apc_paid":null,"fwci":0.3443,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52493261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1132","last_page":"1138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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":0.9965999722480774,"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":0.8511327505111694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7292302846908569},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.708432674407959},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839470863342285},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.48919108510017395},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4728265702724457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46157917380332947},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4421537518501282},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.43935078382492065},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4375871419906616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4089241027832031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3879914879798889},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25861936807632446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15807759761810303},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15697652101516724},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08913412690162659},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08878254890441895}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8511327505111694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292302846908569},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.708432674407959},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839470863342285},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.48919108510017395},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4728265702724457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46157917380332947},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4421537518501282},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43935078382492065},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4375871419906616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4089241027832031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3879914879798889},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25861936807632446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15807759761810303},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15697652101516724},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08913412690162659},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08878254890441895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688142","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G598299161","display_name":null,"funder_award_id":"309629","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1687555731","https://openalex.org/W1936725236","https://openalex.org/W1977331234","https://openalex.org/W2034940213","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2219249508","https://openalex.org/W2313839481","https://openalex.org/W2326699523","https://openalex.org/W2696967604","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2889048668","https://openalex.org/W2899201823","https://openalex.org/W2938134751","https://openalex.org/W2938358845","https://openalex.org/W2963040451","https://openalex.org/W2963881567","https://openalex.org/W2972315886","https://openalex.org/W2972992051","https://openalex.org/W2973000846","https://openalex.org/W3015503328","https://openalex.org/W3024388846","https://openalex.org/W3046380034","https://openalex.org/W3097224504","https://openalex.org/W3103152812","https://openalex.org/W3129570578","https://openalex.org/W6631943919","https://openalex.org/W6688816777","https://openalex.org/W6698643110","https://openalex.org/W6754473786","https://openalex.org/W6770919351","https://openalex.org/W6777811763","https://openalex.org/W6781015976"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W1562475690","https://openalex.org/W1488529827"],"abstract_inverted_index":{"We":[0,74,85],"address":[1],"far-field":[2,94],"speaker":[3,11],"verification":[4],"with":[5,67,97,110],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"based":[10],"embedding":[12],"extractor,":[13],"where":[14],"mismatch":[15],"between":[16],"enrollment":[17],"and":[18,29,46,57,64,78,100,114,125],"test":[19],"data":[20],"often":[21],"comes":[22],"from":[23],"convolutive":[24],"effects":[25],"(e.g.":[26],"room":[27],"reverberation)":[28],"noise.":[30],"To":[31],"mitigate":[32],"these":[33],"effects,":[34],"we":[35],"focus":[36],"on":[37,89,118],"two":[38],"parametric":[39],"normalization":[40,44,50],"methods:":[41],"per-channel":[42],"energy":[43],"(PCEN)":[45],"parameterized":[47],"cepstral":[48],"mean":[49],"(PCMN).":[51],"Both":[52],"methods":[53,104],"contain":[54],"differentiable":[55],"parameters":[56],"thus":[58],"can":[59],"be":[60],"conveniently":[61],"integrated":[62],"to,":[63],"jointly":[65],"optimized":[66],"the":[68,87],"DNN":[69],"using":[70],"automatic":[71],"differentiation":[72],"methods.":[73],"consider":[75],"both":[76],"fixed":[77],"trainable":[79],"(data-driven)":[80],"variants":[81],"of":[82,112],"each":[83],"method.":[84],"evaluate":[86],"performance":[88],"Hi-MIA,":[90],"a":[91],"recent":[92],"large-scale":[93],"speech":[95],"corpus,":[96],"varied":[98],"microphone":[99,124,127],"positional":[101],"settings.":[102],"Our":[103],"outperform":[105],"conventional":[106],"mel":[107],"filterbank":[108],"features,":[109],"maximum":[111],"33.5%":[113],"39.5%":[115],"relative":[116],"improvement":[117],"equal":[119],"error":[120],"rate":[121],"under":[122],"matched":[123],"mismatched":[126],"conditions,":[128],"respectively.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}