{"id":"https://openalex.org/W4416799201","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249126","title":"Interpolating Speaker Identities in Embedding Space for Data Expansion","display_name":"Interpolating Speaker Identities in Embedding Space for Data Expansion","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799201","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249126"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249126","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":"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/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,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","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,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086566120","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0001-8258-7201"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016187230","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0001-9013-0869"},"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,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I R), Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643115","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0002-2536-6426"},"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":"Ke Zhang","raw_affiliation_strings":["SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004441972","display_name":"Jingru Lin","orcid":null},"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":"Jingru Lin","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of 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/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":"Haizhou Li","raw_affiliation_strings":["SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRIBD, School of Artificial Intelligence, The Chinese University of Hong Kong,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"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":0.17645483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"589","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9510999917984009,"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":0.9510999917984009,"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":0.006599999964237213,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0032999999821186066,"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/embedding","display_name":"Embedding","score":0.7949000000953674},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6600000262260437},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5917999744415283},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5231000185012817},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.517799973487854},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3984000086784363}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7949000000953674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805999875068665},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6600000262260437},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249126","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2147774191","https://openalex.org/W2154278880","https://openalex.org/W2407080277","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2973190269","https://openalex.org/W3024869864","https://openalex.org/W3049278490","https://openalex.org/W3111759753","https://openalex.org/W3161294170","https://openalex.org/W3174649707","https://openalex.org/W3198836239","https://openalex.org/W3205635414","https://openalex.org/W3209984917","https://openalex.org/W4205654098","https://openalex.org/W4221154746","https://openalex.org/W4372340947","https://openalex.org/W4392903992","https://openalex.org/W4394744939","https://openalex.org/W4402111801","https://openalex.org/W4402112479","https://openalex.org/W4404576841","https://openalex.org/W4406495581","https://openalex.org/W4408352533","https://openalex.org/W4408355325","https://openalex.org/W4408355810","https://openalex.org/W4415433681"],"related_works":[],"abstract_inverted_index":{"The":[0,101],"success":[1],"of":[2,68],"deep":[3],"learning-based":[4],"speaker":[5,17,56,62,70,75,143],"verification":[6],"systems":[7],"is":[8,26,104,139,163],"largely":[9],"attributed":[10],"to":[11,13,92,96,110,132,177],"access":[12],"large-scale":[14],"and":[15,29,78,169],"diverse":[16],"identity":[18],"data.":[19],"However,":[20],"collecting":[21],"data":[22,50,103,121],"from":[23,72],"more":[24],"identities":[25,57],"expensive,":[27],"challenging,":[28],"often":[30],"limited":[31],"by":[32,58],"privacy":[33],"concerns.":[34],"To":[35],"address":[36],"this":[37],"limitation,":[38],"we":[39,65,145],"propose":[40],"INSIDE":[41,138,162],"(Interpolating":[42],"Speaker":[43],"Identities":[44],"in":[45],"Embedding":[46],"Space),":[47],"a":[48,73,93,156,173],"novel":[49],"expansion":[51],"method":[52],"that":[53,116],"synthesizes":[54],"new":[55],"interpolating":[59],"between":[60],"existing":[61,178],"embeddings.":[63],"Specifically,":[64],"select":[66],"pairs":[67],"nearby":[69],"embeddings":[71,81,88],"pretrained":[74],"embedding":[76],"space":[77],"compute":[79],"intermediate":[80],"using":[82],"spherical":[83],"linear":[84],"interpolation.":[85],"These":[86],"interpolated":[87],"are":[89],"then":[90],"fed":[91],"text-to-speech":[94],"system":[95],"generate":[97],"corresponding":[98],"speech":[99],"waveforms.":[100],"resulting":[102],"combined":[105],"with":[106,119,165],"the":[107],"original":[108],"dataset":[109],"train":[111],"downstream":[112],"models.":[113],"Experiments":[114],"show":[115],"models":[117],"trained":[118,124],"INSIDEexpanded":[120],"outperform":[122],"those":[123],"only":[125],"on":[126,150],"real":[127],"data,":[128],"achieving":[129],"3.06":[130],"%":[131,134,158],"5.24":[133],"relative":[135,159],"improvements.":[136],"While":[137],"primarily":[140],"designed":[141],"for":[142],"verification,":[144],"also":[146],"validate":[147],"its":[148],"effectiveness":[149],"gender":[151],"classification,":[152],"where":[153],"it":[154],"yields":[155],"13.44":[157],"improvement.":[160],"Moreover,":[161],"compatible":[164],"other":[166],"augmentation":[167],"techniques":[168],"can":[170],"serve":[171],"as":[172],"flexible,":[174],"scalable":[175],"addition":[176],"training":[179],"pipelines.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
