{"id":"https://openalex.org/W3099825973","doi":"https://doi.org/10.23919/eusipco47968.2020.9287690","title":"Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments","display_name":"Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3099825973","doi":"https://doi.org/10.23919/eusipco47968.2020.9287690","mag":"3099825973"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287690","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"preprint","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/A5050663411","display_name":"Mohammad Amini","orcid":"https://orcid.org/0000-0003-3765-5070"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mohammad Mohammad Amini","raw_affiliation_strings":["Avignon University"],"affiliations":[{"raw_affiliation_string":"Avignon University","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017334281","display_name":"Driss Matrouf","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Driss Matrouf","raw_affiliation_strings":["Avignon University"],"affiliations":[{"raw_affiliation_string":"Avignon University","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050663411"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":1.32173594,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83936693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983999729156494,"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":0.9939000010490417,"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/robustness","display_name":"Robustness (evolution)","score":0.8613578081130981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503421306610107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6956953406333923},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6259397268295288},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5365158915519714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5182188153266907},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5151785612106323},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5130378007888794},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5083991885185242},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5073358416557312},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4972868263721466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.482289582490921},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45688706636428833},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43752989172935486}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8613578081130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503421306610107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956953406333923},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6259397268295288},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5365158915519714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5182188153266907},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5151785612106323},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5130378007888794},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5083991885185242},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5073358416557312},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4972868263721466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482289582490921},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45688706636428833},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43752989172935486},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287690","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2485419308","https://openalex.org/W2517338937","https://openalex.org/W2557283755","https://openalex.org/W2588997445","https://openalex.org/W2782964974","https://openalex.org/W2805332618","https://openalex.org/W2807305309","https://openalex.org/W2807373279","https://openalex.org/W2888955371","https://openalex.org/W2890964092","https://openalex.org/W2900109395","https://openalex.org/W2916301830","https://openalex.org/W2937328535","https://openalex.org/W2963382494","https://openalex.org/W2963418523","https://openalex.org/W2972986505","https://openalex.org/W2973149417","https://openalex.org/W2981087920","https://openalex.org/W3008883495","https://openalex.org/W3025686075","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W215245425","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489"],"abstract_inverted_index":{"The":[0],"explosion":[1],"of":[2,39,52,93,183],"available":[3],"speech":[4],"data":[5,57,60],"and":[6,58,114],"new":[7],"speaker":[8,25,30,64],"modeling":[9],"methods":[10],"based":[11],"on":[12,111,120],"deep":[13],"neural":[14],"networks":[15],"(DNN)":[16],"have":[17,178],"given":[18],"the":[19,50,55,89,106,115,137,147,164,175],"ability":[20],"to":[21,77,85,125,180],"develop":[22],"more":[23,62,144],"robust":[24,63,145],"recognition":[26,65],"systems.":[27,95],"Among":[28],"DNN":[29],"modelling":[31],"techniques,":[32],"x-vector":[33,104,129,138],"system":[34,139],"has":[35],"shown":[36],"a":[37,127],"degree":[38],"robustness":[40,92],"in":[41,54,69,141,169,174],"noisy":[42,70],"environments.":[43,71],"Previous":[44],"studies":[45],"suggest":[46],"that":[47,158],"by":[48],"increasing":[49],"number":[51],"speakers":[53],"training":[56],"using":[59],"augmentation":[61],"systems":[66],"are":[67],"achievable":[68],"In":[72],"this":[73,97,153],"work,":[74],"we":[75,99,155,177],"want":[76],"know":[78],"if":[79],"explicit":[80,159],"noise":[81,91,160],"compensation":[82,161],"techniques":[83],"continue":[84],"be":[86],"effective":[87],"despite":[88],"general":[90],"these":[94],"For":[96,172],"study,":[98],"will":[100,156],"use":[101],"two":[102],"different":[103],"networks:":[105],"first":[107],"one":[108,117,149],"is":[109,118,143],"trained":[110,119],"Voxceleb1":[112],"(Protocol1),":[113],"second":[116],"Voxceleb1+Voxveleb2":[121],"(Protocol2).":[122],"We":[123],"propose":[124],"add":[126],"denoising":[128,186],"subsystem":[130],"before":[131],"scoring.":[132],"Experimental":[133],"results":[134],"show":[135,157],"that,":[136],"used":[140,150],"Protocol2":[142,176],"than":[146],"other":[148],"Protocol1.":[151],"Despite":[152],"observation":[154],"gives":[162],"almost":[163],"same":[165],"EER":[166,184],"relative":[167],"gain":[168],"both":[170],"protocols.":[171],"example,":[173],"21%":[179],"66%":[181],"improvement":[182],"with":[185],"techniques.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-11-23T00:00:00"}