{"id":"https://openalex.org/W3011755694","doi":"https://doi.org/10.1145/3377170.3377199","title":"Multi-level Data Filter for Speaker Recognition on Imbalanced Datasets","display_name":"Multi-level Data Filter for Speaker Recognition on Imbalanced Datasets","publication_year":2019,"publication_date":"2019-12-20","ids":{"openalex":"https://openalex.org/W3011755694","doi":"https://doi.org/10.1145/3377170.3377199","mag":"3011755694"},"language":"en","primary_location":{"id":"doi:10.1145/3377170.3377199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377170.3377199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City","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/A5100722237","display_name":"Chen Sun","orcid":"https://orcid.org/0000-0002-4142-4008"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Sun","raw_affiliation_strings":["Department of Mathematics, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080037549","display_name":"Yunjie Zhang","orcid":"https://orcid.org/0000-0002-6962-6189"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Zhang","raw_affiliation_strings":["Department of Mathematics, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100348091","display_name":"Yiwei Liu","orcid":"https://orcid.org/0000-0003-2805-7183"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Liu","raw_affiliation_strings":["Department of Mathematics, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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":0.7320347428321838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6370155811309814},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5238842368125916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5062262415885925},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45464783906936646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44009488821029663},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11115562915802002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7320347428321838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6370155811309814},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5238842368125916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062262415885925},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45464783906936646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44009488821029663},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11115562915802002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377170.3377199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377170.3377199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2118978333","https://openalex.org/W2395750323","https://openalex.org/W2551437525","https://openalex.org/W2609296554","https://openalex.org/W2620629206","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2916104401","https://openalex.org/W2936780106","https://openalex.org/W2951019013","https://openalex.org/W2963242190","https://openalex.org/W3103152812","https://openalex.org/W6677390740","https://openalex.org/W6687483927","https://openalex.org/W6745415975","https://openalex.org/W6754808073","https://openalex.org/W6755154125","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W2042327336","https://openalex.org/W289407349"],"abstract_inverted_index":{"End":[0],"to":[1,69],"end":[2],"speaker":[3,11,15,52],"embedding":[4],"systems":[5],"have":[6],"shown":[7],"promising":[8],"performance":[9,50],"on":[10,51,96,105],"recognition":[12,16,53],"tasks.":[13],"However,":[14],"system":[17],"often":[18],"degrade":[19],"obviously":[20],"when":[21],"there":[22],"are":[23,132],"different":[24,110],"scale":[25],"and":[26,44,57,62,74,77,87,99,134],"discrepant":[27],"distribution":[28],"of":[29,41,112,123],"training":[30,126],"datasets.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"proposed":[36,91],"a":[37],"novel":[38],"model":[39,68,92,119],"comprised":[40],"MultiReader":[42,60],"technique":[43,61],"ResNet-GhostVLAD":[45],"network,":[46],"which":[47,84,131],"makes":[48],"the":[49,97,113,121],"task":[54],"more":[55],"stable":[56],"excellent.":[58],"The":[59,90],"dictionary-based":[63],"GhostVLAD":[64],"layer":[65],"enable":[66],"our":[67,118],"filter":[70],"data":[71],"at":[72],"data-level":[73],"feature-level":[75],"respectively,":[76],"make":[78],"it":[79],"robust":[80],"for":[81,109],"imbalanced":[82],"datasets":[83,115],"contain":[85],"noisy":[86],"irrelevant":[88],"information.":[89],"has":[93],"been":[94],"trained":[95],"VoxCeleb":[98],"AISHELL":[100,106],"combined":[101],"dataset,":[102],"then":[103],"tested":[104],"dataset.":[107],"Evaluations":[108],"weights":[111],"multiple":[114],"show":[116],"that":[117],"outperforms":[120],"method":[122],"directly":[124],"mixing":[125],"set":[127],"by":[128],"obvious":[129],"margins,":[130],"10.7%":[133],"44.3%":[135],"relative":[136],"improvement.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}