{"id":"https://openalex.org/W3004253052","doi":"https://doi.org/10.21437/odyssey.2020-66","title":"Analysis of Deep Feature Loss Based Enhancement for Speaker Verification","display_name":"Analysis of Deep Feature Loss Based Enhancement for Speaker Verification","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3004253052","doi":"https://doi.org/10.21437/odyssey.2020-66","mag":"3004253052"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-66","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-66","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.00139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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":false,"raw_author_name":"Phani Sankar Nidadavolu","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":"Jes\u00fas Villalba","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"466"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.7803546786308289},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6766931414604187},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6184665560722351},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5714247226715088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5320229530334473},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48139241337776184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4507170617580414},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4320867955684662},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4285222887992859},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4213102459907532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3955360949039459},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.38079673051834106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35322248935699463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803546786308289},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6766931414604187},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6184665560722351},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5714247226715088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5320229530334473},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48139241337776184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4507170617580414},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4320867955684662},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4285222887992859},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4213102459907532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3955360949039459},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.38079673051834106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35322248935699463},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/odyssey.2020-66","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-66","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.00139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00139","pdf_url":"https://arxiv.org/pdf/2002.00139","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2002.00139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.00139","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":"Preprint"},{"id":"mag:3004253052","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.00139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00139","pdf_url":"https://arxiv.org/pdf/2002.00139","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5799999833106995,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3004253052.pdf","grobid_xml":"https://content.openalex.org/works/W3004253052.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2102605133","https://openalex.org/W2136682440","https://openalex.org/W2140571699","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2331128040","https://openalex.org/W2343593471","https://openalex.org/W2404617565","https://openalex.org/W2516764878","https://openalex.org/W2529337537","https://openalex.org/W2593116425","https://openalex.org/W2600556233","https://openalex.org/W2726515241","https://openalex.org/W2746457594","https://openalex.org/W2808631503","https://openalex.org/W2810843531","https://openalex.org/W2888957357","https://openalex.org/W2890964092","https://openalex.org/W2891237889","https://openalex.org/W2912191105","https://openalex.org/W2916024349","https://openalex.org/W2921683566","https://openalex.org/W2931266113","https://openalex.org/W2938358845","https://openalex.org/W2962866211","https://openalex.org/W2963077989","https://openalex.org/W2963127163","https://openalex.org/W2963403868","https://openalex.org/W2963466847","https://openalex.org/W2963656735","https://openalex.org/W2964299589","https://openalex.org/W2966212213","https://openalex.org/W2970971581","https://openalex.org/W2972392008","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W2981590980","https://openalex.org/W2981921044","https://openalex.org/W2982037672","https://openalex.org/W2984956686","https://openalex.org/W2989863749","https://openalex.org/W2991951409","https://openalex.org/W2998572311","https://openalex.org/W3000589186","https://openalex.org/W3016129867"],"related_works":["https://openalex.org/W3024301174","https://openalex.org/W2982037672","https://openalex.org/W2948661109","https://openalex.org/W2749588430","https://openalex.org/W3088159194","https://openalex.org/W2797972631","https://openalex.org/W2994785103","https://openalex.org/W3211614993","https://openalex.org/W3016595511","https://openalex.org/W3005262054","https://openalex.org/W3160973314","https://openalex.org/W3011500442","https://openalex.org/W2906724656","https://openalex.org/W3041487835","https://openalex.org/W2613495131","https://openalex.org/W2949756029","https://openalex.org/W3031135612","https://openalex.org/W3199713199","https://openalex.org/W2810843531","https://openalex.org/W3037737213"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,191],"is":[2,27],"conventionally":[3],"used":[4],"to":[5,37,116,161,183,220],"inject":[6],"robustness":[7],"in":[8,42,86,133,167],"Speaker":[9],"Verification":[10],"systems.":[11],"Several":[12],"recently":[13],"organized":[14],"challenges":[15],"focus":[16],"on":[17,66],"handling":[18],"novel":[19,84],"acoustic":[20],"environments.":[21],"Deep":[22],"learning":[23],"based":[24,64],"speech":[25,69],"enhancement":[26,40,102,125,201,227],"a":[28,34,47,67,118,185],"modern":[29],"solution":[30],"for":[31,92,124,145,193,229],"this.":[32],"Recently,":[33],"study":[35,182],"proposed":[36],"optimize":[38],"the":[39,43,60,107,130,146,175,198],"network":[41,97,126],"activation":[44],"space":[45],"of":[46,78,95,109,200,203,223],"pre-trained":[48],"auxiliary":[49,96],"network.":[50],"This":[51,73],"methodology,":[52],"called":[53,71],"deep":[54,224],"feature":[55,103,225],"loss,":[56],"greatly":[57],"improved":[58],"over":[59,174],"state-of-the-art":[61],"conventional":[62],"x-vector":[63,189],"system":[65],"children":[68],"dataset":[70],"BabyTrain.":[72],"work":[74],"analyzes":[75],"various":[76],"facets":[77],"that":[79,87,113,208],"approach":[80],"and":[81,101,121],"asks":[82],"few":[83],"questions":[85],"context.":[88],"We":[89,177],"first":[90],"search":[91],"optimal":[93],"number":[94],"activations,":[98],"training":[99],"data,":[100],"dimension.":[104],"Experiments":[105],"reveal":[106],"importance":[108],"Signal-to-Noise":[110],"Ratio":[111],"filtering":[112],"we":[114,135,154,196,215],"employ":[115],"create":[117],"large,":[119],"clean,":[120],"naturalistic":[122],"corpus":[123],"training.":[127,213],"To":[128],"counter":[129],"\"mismatch\"":[131],"problem":[132],"enhancement,":[134],"find":[136,155],"enhancing":[137],"front-end":[138],"(x-vector":[139],"network)":[140],"data":[141,190],"helpful":[142],"while":[143],"harmful":[144],"back-end":[147],"(Probabilistic":[148],"Linear":[149],"Discriminant":[150],"Analysis":[151],"(PLDA)).":[152],"Importantly,":[153],"enhanced":[156],"signals":[157],"contain":[158],"complementary":[159],"information":[160],"original.":[162],"Established":[163],"by":[164],"combining":[165],"them":[166],"front-end,":[168],"this":[169,230],"gives":[170],"~40%":[171],"relative":[172],"improvement":[173],"baseline.":[176],"also":[178],"do":[179],"an":[180],"ablation":[181],"remove":[184],"noise":[186,209],"class":[187,210],"from":[188],"and,":[192],"such":[194],"systems,":[195],"establish":[197],"utility":[199],"regardless":[202],"whether":[204],"it":[205],"has":[206],"seen":[207],"itself":[211],"during":[212],"Finally,":[214],"design":[216],"several":[217],"dereverberation":[218],"schemes":[219],"conclude":[221],"ineffectiveness":[222],"loss":[226],"scheme":[228],"task.":[231]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}