{"id":"https://openalex.org/W2982037672","doi":"https://doi.org/10.1109/icassp40776.2020.9053110","title":"Feature Enhancement with Deep Feature Losses for Speaker Verification","display_name":"Feature Enhancement with Deep Feature Losses for Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982037672","doi":"https://doi.org/10.1109/icassp40776.2020.9053110","mag":"2982037672"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053110","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":"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/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":true,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, 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"]}]},{"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":["Center for Language and Speech Processing, Johns Hopkins University, 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"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"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":"Nanxin Chen","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, 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"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, 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"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014918159"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":3.314,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93380416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7584","last_page":"7588"},"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":0.9994000196456909,"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":0.7809104323387146},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6758347749710083},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6261016130447388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001771092414856},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5897862911224365},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5664211511611938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5464422106742859},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5441128611564636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5291198492050171},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5193308591842651},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4933268129825592},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4932853579521179},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48236387968063354},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46654012799263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0776238739490509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809104323387146},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6758347749710083},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6261016130447388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001771092414856},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5897862911224365},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5664211511611938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5464422106742859},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5441128611564636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5291198492050171},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5193308591842651},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4933268129825592},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4932853579521179},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48236387968063354},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46654012799263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0776238739490509},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053110","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1574170747","https://openalex.org/W1983108229","https://openalex.org/W2219249508","https://openalex.org/W2331128040","https://openalex.org/W2343593471","https://openalex.org/W2516764878","https://openalex.org/W2527915734","https://openalex.org/W2746457594","https://openalex.org/W2765833400","https://openalex.org/W2808631503","https://openalex.org/W2916024349","https://openalex.org/W2936028438","https://openalex.org/W2963341071","https://openalex.org/W2963420686","https://openalex.org/W2972392008","https://openalex.org/W2972425344","https://openalex.org/W2972443522","https://openalex.org/W2973193289","https://openalex.org/W2979593053","https://openalex.org/W2989863749","https://openalex.org/W3008883495","https://openalex.org/W3016143998","https://openalex.org/W4232282348","https://openalex.org/W4288558760","https://openalex.org/W6634468015","https://openalex.org/W6688816777","https://openalex.org/W6702130928","https://openalex.org/W6743731764","https://openalex.org/W6745378982","https://openalex.org/W6753100508","https://openalex.org/W6760112457","https://openalex.org/W6768553363","https://openalex.org/W6769861357","https://openalex.org/W6770522430"],"related_works":["https://openalex.org/W1600259599","https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W4214692512","https://openalex.org/W3176700874","https://openalex.org/W2687223163","https://openalex.org/W2786094008","https://openalex.org/W3131501806","https://openalex.org/W2799683370","https://openalex.org/W2807745940"],"abstract_inverted_index":{"Speaker":[0],"Verification":[1],"still":[2],"suffers":[3],"from":[4],"the":[5,16,43,47,61,107],"challenge":[6],"of":[7,51,93,120],"generalization":[8],"to":[9,36],"novel":[10],"adverse":[11],"environments.":[12,98],"We":[13,34,58,99],"leverage":[14],"on":[15,63,84],"recent":[17],"advancements":[18],"made":[19],"by":[20],"deep":[21],"learning":[22],"based":[23,32],"speech":[24],"enhancement":[25,44],"and":[26,65,122,126],"propose":[27,35],"a":[28,52],"feature-domain":[29],"supervised":[30],"denoising":[31],"solution.":[33],"use":[37],"Deep":[38],"Feature":[39],"Loss":[40],"which":[41,91],"optimizes":[42],"network":[45],"in":[46,96,103,124],"hidden":[48],"activation":[49],"space":[50],"pre-trained":[53],"auxiliary":[54],"speaker":[55],"embedding":[56],"network.":[57],"experimentally":[59],"verify":[60],"approach":[62],"simulated":[64,69],"real":[66,85],"data.":[67],"A":[68],"testing":[70],"setup":[71],"is":[72],"created":[73],"using":[74],"various":[75],"noise":[76],"types":[77],"at":[78],"different":[79],"SNR":[80],"levels.":[81],"For":[82],"evaluation":[83],"data,":[86],"we":[87,116],"choose":[88],"BabyTrain":[89,114],"corpus":[90],"consists":[92],"children":[94],"recordings":[95],"uncontrolled":[97],"observe":[100,117],"consistent":[101],"gains":[102,119],"every":[104],"condition":[105],"over":[106],"state-of-the-art":[108],"augmented":[109],"Factorized-TDNN":[110],"x-vector":[111],"system.":[112],"On":[113],"corpus,":[115],"relative":[118],"10.38%":[121],"12.40%":[123],"minDCF":[125],"EER":[127],"respectively.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}