{"id":"https://openalex.org/W4416798653","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249009","title":"Voice Conversion Augmentation for Speaker Recognition on Defective Datasets","display_name":"Voice Conversion Augmentation for Speaker Recognition on Defective Datasets","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798653","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249009"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore,Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000218886","display_name":"Zhan Shi","orcid":"https://orcid.org/0000-0001-9717-1487"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Shi","raw_affiliation_strings":["The Chinese University of Hong Kong, School of Artificial Intelligence,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, School of Artificial Intelligence,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111432082","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0002-2317-9571"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":["National University of Singapore,Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["National University of Singapore,Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":"2529","last_page":"2534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9223999977111816,"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":0.9223999977111816,"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":0.031099999323487282,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.005400000140070915,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7307999730110168},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.570900022983551},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5511000156402588},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.3901999890804291},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967000007629395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.746999979019165},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7307999730110168},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.570900022983551},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593999981880188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28189998865127563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":32,"referenced_works":["https://openalex.org/W2041823554","https://openalex.org/W2087240369","https://openalex.org/W2154278880","https://openalex.org/W2194775991","https://openalex.org/W2516764878","https://openalex.org/W2576309025","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2938583109","https://openalex.org/W2972359262","https://openalex.org/W2972450593","https://openalex.org/W2973190269","https://openalex.org/W2998588665","https://openalex.org/W2998845736","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3042609801","https://openalex.org/W3098557217","https://openalex.org/W3145003630","https://openalex.org/W3163150275","https://openalex.org/W3180863154","https://openalex.org/W3205635414","https://openalex.org/W4205654098","https://openalex.org/W4250328251","https://openalex.org/W4292348150","https://openalex.org/W4297841773","https://openalex.org/W4372348291","https://openalex.org/W4376457010","https://openalex.org/W4385823321","https://openalex.org/W4388579618"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"speaker":[1,129],"recognition":[2,130],"system":[3],"relies":[4],"on":[5,109],"abundant":[6],"and":[7,21],"balanced":[8],"datasets":[9,112],"for":[10,35,126],"classification":[11],"training.":[12],"However,":[13,42],"diverse":[14],"defective":[15],"datasets,":[16,23],"such":[17],"as":[18],"partially-labelled,":[19],"small-scale,":[20],"imbalanced":[22],"are":[24,96],"common":[25],"in":[26,50,102],"real-world":[27],"applications.":[28],"Previous":[29],"works":[30],"usually":[31],"studied":[32],"specific":[33],"solutions":[34],"each":[36],"scenario":[37],"from":[38,73,93,132],"the":[39,43,63,74,84,99,103,128,133],"algorithm":[40],"perspective.":[41],"root":[44],"cause":[45],"of":[46],"these":[47,55,118],"problems":[48,131],"lies":[49],"dataset":[51,119],"imperfections.":[52],"To":[53],"address":[54],"challenges":[56],"with":[57],"a":[58,123],"unified":[59],"solution,":[60],"we":[61,82],"propose":[62],"Voice":[64],"Conversion":[65],"Augmentation":[66],"(VCA)":[67],"strategy":[68,88],"to":[69,78,89,98],"obtain":[70],"pseudo":[71],"speech":[72,92,101],"training":[75],"set.":[76],"Furthermore,":[77],"guarantee":[79],"generation":[80],"quality,":[81],"designed":[83],"VCA-NN":[85,115],"(nearest":[86],"neighbours)":[87],"select":[90],"source":[91],"utterances":[94],"that":[95,114],"close":[97],"target":[100],"representation":[104],"space.":[105],"Our":[106],"experimental":[107],"results":[108],"three":[110],"created":[111],"demonstrated":[113],"effectively":[116],"mitigates":[117],"problems,":[120],"which":[121],"provides":[122],"new":[124],"direction":[125],"handling":[127],"data":[134],"aspect.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}