{"id":"https://openalex.org/W3201897989","doi":"https://doi.org/10.1109/asru51503.2021.9688006","title":"Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification","display_name":"Optimized Power Normalized Cepstral Coefficients Towards Robust Deep Speaker Verification","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3201897989","doi":"https://doi.org/10.1109/asru51503.2021.9688006","mag":"3201897989"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688006","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.12058","any_repository_has_fulltext":true},"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":0.5076,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6589964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"abs 1510 8484","issue":null,"first_page":"185","last_page":"190"},"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":0.9994999766349792,"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":0.9912999868392944,"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/speaker-verification","display_name":"Speaker verification","score":0.8243209719657898},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6784883737564087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6708622574806213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6639243364334106},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6267396807670593},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44805335998535156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39871323108673096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35508227348327637},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3110484480857849}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8243209719657898},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6784883737564087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708622574806213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6639243364334106},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6267396807670593},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44805335998535156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39871323108673096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35508227348327637},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3110484480857849}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688006","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"},{"id":"pmh:oai:arXiv.org:2109.12058","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12058","pdf_url":"https://arxiv.org/pdf/2109.12058","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":"pmh:oai:HAL:hal-03359173v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-03359173","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ASRU 2021 - IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2021, Cartagena, Colombia","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2109.12058","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.12058","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.12058","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12058","pdf_url":"https://arxiv.org/pdf/2109.12058","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":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W654137760","https://openalex.org/W1489184006","https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W1936725236","https://openalex.org/W2114719288","https://openalex.org/W2129388674","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2326699523","https://openalex.org/W2588576637","https://openalex.org/W2612434969","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2899201823","https://openalex.org/W2928556070","https://openalex.org/W2938358845","https://openalex.org/W2962788625","https://openalex.org/W2963881567","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2973157397","https://openalex.org/W2991951409","https://openalex.org/W3004720752","https://openalex.org/W3004940340","https://openalex.org/W3046380034","https://openalex.org/W3103152812","https://openalex.org/W3104056985","https://openalex.org/W3137249133","https://openalex.org/W3160743249","https://openalex.org/W3161792602","https://openalex.org/W6631190155","https://openalex.org/W6635152626","https://openalex.org/W6679172546","https://openalex.org/W6688816777","https://openalex.org/W6737575990","https://openalex.org/W6740167877","https://openalex.org/W6771538394"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2543208657","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W66821593"],"abstract_inverted_index":{"After":[0],"their":[1],"introduction":[2],"to":[3,16],"robust":[4],"speech":[5],"recognition,":[6],"power":[7,32],"normalized":[8],"cepstral":[9],"coefficient":[10],"(PNCC)":[11],"features":[12],"were":[13],"successfully":[14],"adopted":[15],"other":[17],"tasks,":[18],"including":[19],"speaker":[20,53,59,92],"verification.":[21],"However,":[22],"as":[23],"a":[24,90],"feature":[25],"extractor":[26],"with":[27,89],"long-term":[28],"operations":[29],"on":[30,42,62,101,118],"the":[31],"spectrogram,":[33],"its":[34,78],"temporal":[35],"processing":[36],"and":[37,73,81,104,111,120],"amplitude":[38],"scaling":[39],"steps":[40],"dedicated":[41],"environmental":[43],"compensation":[44],"may":[45],"be":[46],"redundant.":[47],"Further,":[48],"they":[49],"might":[50],"suppress":[51],"intrinsic":[52],"variations":[54],"that":[55],"are":[56],"useful":[57],"for":[58],"verification":[60,93],"based":[61],"deep":[63],"neural":[64],"networks":[65],"(DNN).":[66],"Therefore,":[67],"in":[68],"this":[69],"study,":[70],"we":[71],"revisit":[72],"optimize":[74],"PNCCs":[75,100],"by":[76,82,108],"ablating":[77],"medium-time":[79],"processor":[80],"introducing":[83],"channel":[84],"energy":[85],"normalization.":[86],"Experimental":[87],"results":[88],"DNN-based":[91],"system":[94],"indicate":[95],"substantial":[96],"improvement":[97],"over":[98],"baseline":[99],"both":[102],"in-domain":[103],"cross-domain":[105],"scenarios,":[106],"reflected":[107],"relatively":[109],"5.8%":[110],"61.2%":[112],"maximum":[113],"lower":[114],"equal":[115],"error":[116],"rate":[117],"VoxCelebl":[119],"VoxMovies,":[121],"respectively.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2021-10-11T00:00:00"}