{"id":"https://openalex.org/W3134490682","doi":"https://doi.org/10.1109/iscslp49672.2021.9362090","title":"Speaker Embedding Augmentation with Noise Distribution Matching","display_name":"Speaker Embedding Augmentation with Noise Distribution Matching","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3134490682","doi":"https://doi.org/10.1109/iscslp49672.2021.9362090","mag":"3134490682"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050425","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-9597-9829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363653","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0002-7341-4904"},"institutions":[{"id":"https://openalex.org/I4210115303","display_name":"Moscow University \u00abSynergy\u00bb","ror":"https://ror.org/028mtfb17","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210115303"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology","institution_ids":["https://openalex.org/I4210115303","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","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":0.998199999332428,"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":0.9976999759674072,"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/embedding","display_name":"Embedding","score":0.8583506345748901},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7487590312957764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6775208711624146},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6011618971824646},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5622112154960632},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.560619592666626},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5517779588699341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49868083000183105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4176377058029175},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41033509373664856},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3910647928714752},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3711978495121002},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2251531183719635},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10641562938690186},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10173606872558594},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07100820541381836}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8583506345748901},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7487590312957764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775208711624146},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6011618971824646},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5622112154960632},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.560619592666626},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5517779588699341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49868083000183105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4176377058029175},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41033509373664856},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3910647928714752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3711978495121002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2251531183719635},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10641562938690186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10173606872558594},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07100820541381836},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/iscslp49672.2021.9362090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1959608418","https://openalex.org/W2046056978","https://openalex.org/W2099471712","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2404617565","https://openalex.org/W2406778302","https://openalex.org/W2748318213","https://openalex.org/W2748488820","https://openalex.org/W2888968865","https://openalex.org/W2890654588","https://openalex.org/W2890964092","https://openalex.org/W2944613371","https://openalex.org/W2956925952","https://openalex.org/W2962788625","https://openalex.org/W2963371159","https://openalex.org/W2963382494","https://openalex.org/W2963702081","https://openalex.org/W2972668418","https://openalex.org/W2972986505","https://openalex.org/W2981461916","https://openalex.org/W3010925296","https://openalex.org/W4288091954","https://openalex.org/W4320013936","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6713287686","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W2081900870","https://openalex.org/W1979583797","https://openalex.org/W3162204513","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2371138613","https://openalex.org/W2080135837","https://openalex.org/W2793679056","https://openalex.org/W2048963458"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,23,41,142],"(DA)":[2],"is":[3,75],"an":[4],"effective":[5],"strategy":[6],"to":[7,27,46,76,82,139],"help":[8],"building":[9],"robust":[10],"systems":[11],"with":[12],"good":[13],"generalization":[14],"ability.":[15],"In":[16],"the":[17,29,34,38,47,68,84,87,110,117,140],"embedding":[18,31,70],"based":[19,65],"speaker":[20,69,93],"verification,":[21],"data":[22],"could":[24,106,120],"be":[25,107,121],"applied":[26],"either":[28],"front-end":[30],"extractor":[32],"or":[33],"back-end":[35,40],"PLDA.":[36],"Unlike":[37],"conventional":[39,141],"method":[42],"which":[43,132],"adds":[44],"noises":[45],"raw":[48],"audios":[49],"and":[50,89,135],"then":[51],"extracts":[52],"augmented":[53,91],"embeddings,":[54],"in":[55,67],"this":[56],"work,":[57],"we":[58,114],"proposed":[59,118],"a":[60,126],"noise":[61],"distribution":[62],"matching":[63],"(NDM)":[64],"algorithm":[66],"space.":[71],"The":[72],"basic":[73],"idea":[74],"use":[77],"distributions":[78],"such":[79],"as":[80],"Gaussian":[81],"model":[83],"difference":[85],"between":[86],"clean":[88],"original":[90],"noisy":[92],"embeddings.":[94],"Experiments":[95],"are":[96],"carried":[97],"out":[98],"on":[99],"SRE16":[100],"dataset,":[101],"where":[102],"consistent":[103],"performance":[104],"improvement":[105],"obtained":[108],"by":[109],"novel":[111],"NDM.":[112],"Furthermore,":[113],"found":[115],"that":[116],"NDM":[119],"robustly":[122],"estimated":[123],"using":[124],"only":[125],"small":[127],"amount":[128],"of":[129],"training":[130],"data,":[131],"saves":[133],"time":[134],"disk":[136],"cost":[137],"compared":[138],"method.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}