{"id":"https://openalex.org/W4205567651","doi":"https://doi.org/10.1109/rivf51545.2021.9642074","title":"Improving Speaker Verification in Noisy Environment Using DNN Classifier","display_name":"Improving Speaker Verification in Noisy Environment Using DNN Classifier","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W4205567651","doi":"https://doi.org/10.1109/rivf51545.2021.9642074"},"language":"en","primary_location":{"id":"doi:10.1109/rivf51545.2021.9642074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5068095015","display_name":"Chung Tran Quang","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Chung Tran Quang","raw_affiliation_strings":["Vietnam Artificial Intelligence Solutions, Hanoi University of Science and Technology, Ha Noi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence Solutions, Hanoi University of Science and Technology, Ha Noi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691795","display_name":"Quang Minh Nguyen","orcid":"https://orcid.org/0000-0003-2951-8332"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quang Minh Nguyen","raw_affiliation_strings":["Vietnam Artificial Intelligence Solutions, FPT University, Ha Noi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence Solutions, FPT University, Ha Noi, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067573637","display_name":"Pham Ngoc Phuong","orcid":"https://orcid.org/0000-0002-7741-3570"},"institutions":[{"id":"https://openalex.org/I4210115718","display_name":"Thai Nguyen University","ror":"https://ror.org/02128gy91","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210115718"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham Ngoc Phuong","raw_affiliation_strings":["Thai Nguyen University, Vietnam, Thai Nguyen, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thai Nguyen University, Vietnam, Thai Nguyen, Vietnam","institution_ids":["https://openalex.org/I4210115718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110936633","display_name":"Quoc Truong","orcid":"https://orcid.org/0009-0008-8098-2492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Vietnam Artificial Intelligence Solutions, Ha Noi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vietnam Artificial Intelligence Solutions, Ha Noi, Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20203135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.8141424655914307},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7257357835769653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5972445607185364},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5906846523284912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339727401733398},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5307733416557312},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4989786148071289},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49802660942077637},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4728719890117645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45765814185142517},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4172079563140869},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4106053411960602},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40479257702827454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35634341835975647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141424655914307},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7257357835769653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5972445607185364},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5906846523284912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339727401733398},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5307733416557312},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4989786148071289},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49802660942077637},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4728719890117645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45765814185142517},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4172079563140869},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4106053411960602},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40479257702827454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35634341835975647},{"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/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf51545.2021.9642074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2039057510","https://openalex.org/W2101556109","https://openalex.org/W2129379984","https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2219249508","https://openalex.org/W2579763951","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2807627734","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2967957380","https://openalex.org/W2972627751","https://openalex.org/W3019117105","https://openalex.org/W3025515949","https://openalex.org/W6635152626","https://openalex.org/W6740167877"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W1996621592","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,35],"in":[2,39,61,87,105],"noisy":[3,56,88,149],"environments":[4],"is":[5,28,37,84],"still":[6,85],"a":[7,31,111,141],"challenging":[8],"task.":[9],"Previous":[10],"studies":[11,50],"have":[12],"proposed":[13,131],"speaker":[14,100],"embeddings":[15],"(x-vectors,":[16],"ThinResNet)":[17],"with":[18,123],"classifier":[19,114],"models":[20,102],"(PLDA,":[21],"cosine)":[22],"to":[23,53,70],"classify":[24],"if":[25],"an":[26,43],"audio":[27],"spoken":[29],"by":[30,58,137],"specific":[32],"speaker.":[33],"The":[34],"process":[36],"defined":[38],"3":[40],"steps:":[41],"training":[42],"embedding":[44,63,101,118],"extractor,":[45],"enrollment":[46],"and":[47,103,108,120,145],"verification.":[48],"Most":[49],"were":[51],"trying":[52],"mitigate":[54],"the":[55,62,68,77,81,96,130,134],"issue":[57],"augmenting":[59],"noises":[60],"extractor.":[64],"This":[65],"method":[66],"helps":[67],"extractor":[69],"tolerate":[71],"more":[72],"types":[73],"of":[74,98,117],"noise":[75],"during":[76],"inference":[78],"process.":[79],"However,":[80],"classification":[82],"model":[83],"sensitive":[86],"environments.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"(1)":[94],"evaluate":[95],"effectiveness":[97],"different":[99],"classifiers":[104],"various":[106],"conditions,":[107],"(2)":[109],"propose":[110],"neural":[112],"network":[113],"on":[115,140,148],"top":[116],"vectors":[119],"train":[121],"it":[122],"data":[124],"augmentation.":[125],"Experimental":[126],"results":[127],"indicate":[128],"that":[129],"pipeline":[132,136],"outperforms":[133],"traditional":[135],"5%":[138],"F1":[139,147],"clean":[142],"test":[143,150],"set":[144],"9%":[146],"sets.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}