{"id":"https://openalex.org/W4408354295","doi":"https://doi.org/10.1109/icassp49660.2025.10889777","title":"A Noisy Label Filter based on GMM Binary Classification for Speaker Verification","display_name":"A Noisy Label Filter based on GMM Binary Classification for Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354295","doi":"https://doi.org/10.1109/icassp49660.2025.10889777"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5109475001","display_name":"J. Yao","orcid":"https://orcid.org/0009-0007-5433-5868"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianglong Yao","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310820","display_name":"Shenghui Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghui Lu","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049791364","display_name":"Pengyu Ren","orcid":"https://orcid.org/0000-0002-0116-0554"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyu Ren","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113251188","display_name":"Kaidi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaidi Wang","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109475001"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":2.0204,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86883623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9883000254631042,"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":0.9883000254631042,"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":0.9861000180244446,"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":0.7596062421798706},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.716255784034729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6628495454788208},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5494307279586792},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5138269066810608},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48641276359558105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4525451362133026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4525030851364136},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.44157612323760986},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4313989281654358},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.18441706895828247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13228154182434082},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07212135195732117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596062421798706},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.716255784034729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6628495454788208},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5494307279586792},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5138269066810608},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48641276359558105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4525451362133026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4525030851364136},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.44157612323760986},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4313989281654358},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.18441706895828247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13228154182434082},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07212135195732117},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2296073425","https://openalex.org/W2403681572","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963509340","https://openalex.org/W2963697299","https://openalex.org/W2964292098","https://openalex.org/W2979302305","https://openalex.org/W2981087920","https://openalex.org/W2981873476","https://openalex.org/W3024869864","https://openalex.org/W3042609801","https://openalex.org/W3142849873","https://openalex.org/W3197627775","https://openalex.org/W3206287456","https://openalex.org/W4206908380","https://openalex.org/W4226254439","https://openalex.org/W4287947470","https://openalex.org/W4385822671","https://openalex.org/W4392902963","https://openalex.org/W6762161020","https://openalex.org/W6768848008","https://openalex.org/W6769178842","https://openalex.org/W6771630921","https://openalex.org/W6789476682"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Noisy":[0],"labels":[1,9,37,116],"are":[2,96],"inevitable":[3],"in":[4],"real-world":[5,106],"datasets.":[6],"These":[7,94],"noisy":[8,36,92,115],"cause":[10],"deep":[11],"neural":[12],"networks":[13],"to":[14,22,71],"gradient":[15],"descent":[16],"towards":[17],"the":[18,50,73,86],"wrong":[19],"direction,":[20],"leading":[21],"performance":[23],"degradation.":[24],"In":[25],"this":[26],"paper,":[27],"We":[28,40,102],"propose":[29],"an":[30,42],"efficient":[31],"method":[32,126],"for":[33,45],"filtering":[34],"out":[35,85],"during":[38],"training.":[39],"calculate":[41],"embedding":[43,56,61],"center":[44],"each":[46,54],"speaker":[47,60],"and":[48,57,83],"compute":[49],"cosine":[51,81],"similarity":[52,90],"between":[53],"audio":[55],"its":[58],"corresponding":[59],"center.":[62],"Subsequently,":[63],"we":[64],"use":[65],"a":[66],"Gaussian":[67],"Mixture":[68],"Model":[69],"(GMM)":[70],"classify":[72],"samples":[74],"into":[75],"two":[76],"categories":[77],"based":[78],"on":[79,105],"their":[80],"similarities":[82],"filter":[84],"class":[87],"with":[88,112],"lower":[89],"as":[91,108,110],"labels.":[93],"steps":[95],"iterated":[97],"until":[98],"training":[99],"is":[100],"complete.":[101],"conducted":[103],"experiments":[104],"datasets":[107],"well":[109],"scenarios":[111],"artificially":[113],"added":[114],"of":[117],"different":[118],"types.":[119],"The":[120],"experimental":[121],"results":[122],"demonstrate":[123],"that":[124],"our":[125],"achieved":[127],"notable":[128],"performance.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-09T06:09:20.037420","created_date":"2025-10-10T00:00:00"}