{"id":"https://openalex.org/W2981921044","doi":"https://doi.org/10.1109/icassp40776.2020.9053823","title":"Unsupervised Feature Enhancement for Speaker Verification","display_name":"Unsupervised Feature Enhancement for Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981921044","doi":"https://doi.org/10.1109/icassp40776.2020.9053823","mag":"2981921044"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005758272","display_name":"Phani Sankar Nidadavolu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Phani Sankar Nidadavolu","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044321467","display_name":"Paola Garc\u00eda-Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia-Perera","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"[Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA]","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005758272"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.14777568,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38581486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7599","last_page":"7603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.7728983163833618},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.767353892326355},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7080948948860168},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6009108424186707},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5872699022293091},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5833246111869812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5822792649269104},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5765915513038635},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5368396043777466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49458834528923035},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47263452410697937},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.47187820076942444},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4697416424751282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45264720916748047},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.42822617292404175},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4276406168937683},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4196249842643738},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1317339539527893},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09112584590911865},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06439101696014404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728983163833618},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.767353892326355},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7080948948860168},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6009108424186707},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5872699022293091},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5833246111869812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5822792649269104},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5765915513038635},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5368396043777466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49458834528923035},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47263452410697937},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.47187820076942444},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4697416424751282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45264720916748047},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.42822617292404175},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4276406168937683},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4196249842643738},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1317339539527893},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09112584590911865},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06439101696014404},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11915","pdf_url":"https://arxiv.org/pdf/1910.11915","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":"mag:2981921044","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11915","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.11915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11915","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/njw5-w339","is_oa":true,"landing_page_url":"https://doi.org/10.17023/njw5-w339","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11915","pdf_url":"https://arxiv.org/pdf/1910.11915","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981921044.pdf","grobid_xml":"https://content.openalex.org/works/W2981921044.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1569447338","https://openalex.org/W1574170747","https://openalex.org/W1983812858","https://openalex.org/W2099471712","https://openalex.org/W2164502538","https://openalex.org/W2289394825","https://openalex.org/W2516764878","https://openalex.org/W2593414223","https://openalex.org/W2726515241","https://openalex.org/W2746457594","https://openalex.org/W2808631503","https://openalex.org/W2888858245","https://openalex.org/W2890964092","https://openalex.org/W2916024349","https://openalex.org/W2931266113","https://openalex.org/W2936028438","https://openalex.org/W2962793481","https://openalex.org/W2972359262","https://openalex.org/W2972425344","https://openalex.org/W2972961496","https://openalex.org/W2973193289","https://openalex.org/W2979593053","https://openalex.org/W2989863749","https://openalex.org/W3008883495","https://openalex.org/W6633847657","https://openalex.org/W6634468015","https://openalex.org/W6760112457","https://openalex.org/W6768553363"],"related_works":["https://openalex.org/W2739016327","https://openalex.org/W2046056978","https://openalex.org/W1809172870","https://openalex.org/W95717433","https://openalex.org/W89100185","https://openalex.org/W3010846554","https://openalex.org/W1996917409","https://openalex.org/W2766245080","https://openalex.org/W2586956420","https://openalex.org/W3152661456","https://openalex.org/W2944613371","https://openalex.org/W2887833611","https://openalex.org/W3182396116","https://openalex.org/W2517796218","https://openalex.org/W1508297597","https://openalex.org/W2950744995","https://openalex.org/W3042722625","https://openalex.org/W2124248639","https://openalex.org/W2900575527","https://openalex.org/W2764072168"],"abstract_inverted_index":{"The":[0,62,80],"task":[1],"of":[2,18,35,64],"making":[3],"speaker":[4,37,98],"verification":[5,38,99],"systems":[6],"robust":[7],"to":[8,57],"adverse":[9,49],"scenarios":[10],"remain":[11],"a":[12],"challenging":[13],"and":[14,51,76,88,116],"an":[15,22],"active":[16],"area":[17],"research.":[19],"We":[20,40],"developed":[21],"unsupervised":[23],"feature":[24],"enhancement":[25,60,120],"approach":[26,66,81,121],"in":[27,48,97],"log-filter":[28],"bank":[29],"domain":[30],"with":[31,42],"the":[32,59,65],"end":[33],"goal":[34],"improving":[36],"performance.":[39],"experimented":[41],"using":[43],"both":[44,86],"real":[45,87],"speech":[46,53],"recorded":[47],"environments":[50],"degraded":[52],"obtained":[54],"by":[55,69],"simulation":[56],"train":[58],"systems.":[61],"effectiveness":[63],"was":[67,94,103,112],"shown":[68],"testing":[70],"on":[71,85],"several":[72],"real,":[73],"simulated":[74,89],"noisy,":[75],"reverberant":[77],"test":[78],"sets.":[79],"yielded":[82,122],"significant":[83],"improvements":[84],"sets":[90],"when":[91],"data":[92,110],"augmentation":[93,102,111],"not":[95],"used":[96,104,113],"pipeline":[100],"or":[101],"only":[105],"during":[106],"x-vector":[107,115],"training.":[108],"When":[109],"for":[114],"PLDA":[117],"training,":[118],"our":[119],"slight":[123],"improvements.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
