{"id":"https://openalex.org/W4406461534","doi":"https://doi.org/10.1109/slt61566.2024.10832140","title":"Speaker Contrastive Learning For Source Speaker Tracing","display_name":"Speaker Contrastive Learning For Source Speaker Tracing","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461534","doi":"https://doi.org/10.1109/slt61566.2024.10832140"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542472","display_name":"Hongmei Guo","orcid":"https://orcid.org/0000-0003-4082-7363"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmei Guo","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779996","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0002-6815-858X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101001568","display_name":"Mengjie Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjie Du","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454072","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-1558-8623"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036533907","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-4039-2411"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1247","last_page":"1253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9980999827384949,"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":0.7852622270584106},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.6225054860115051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5133547186851501},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4557565748691559},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4171163737773895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3207824230194092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852622270584106},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.6225054860115051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5133547186851501},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4557565748691559},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4171163737773895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3207824230194092},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2123299109","https://openalex.org/W2219249508","https://openalex.org/W2405506115","https://openalex.org/W2519091744","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962747881","https://openalex.org/W2963077926","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2969985801","https://openalex.org/W2972908178","https://openalex.org/W3024869864","https://openalex.org/W3083423753","https://openalex.org/W3095570773","https://openalex.org/W3163475957","https://openalex.org/W3165478005","https://openalex.org/W3197659778","https://openalex.org/W3197763626","https://openalex.org/W3202267900","https://openalex.org/W3213785244","https://openalex.org/W4221154745","https://openalex.org/W4283458492","https://openalex.org/W4319862431","https://openalex.org/W4372260053","https://openalex.org/W4372260476","https://openalex.org/W4375868976","https://openalex.org/W4385822891","https://openalex.org/W4385823240","https://openalex.org/W4385823264","https://openalex.org/W4385823432","https://openalex.org/W4385823472","https://openalex.org/W4385975749","https://openalex.org/W4392969497","https://openalex.org/W4399511042","https://openalex.org/W4400033122","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6688816777","https://openalex.org/W6763832098","https://openalex.org/W6795261426","https://openalex.org/W6802029025","https://openalex.org/W6805710207","https://openalex.org/W6839093550","https://openalex.org/W6843707108","https://openalex.org/W6868951627"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"As":[0],"a":[1,45,60,118,139],"form":[2],"of":[3,9,15,27,151,201],"biometric":[4],"authentication":[5],"technology,":[6],"the":[7,70,82,109,129,149,152,161,172,177,185,198,204,212],"security":[8],"speaker":[10,84,95,119,125,132,145,156,164,169,181,193],"verification":[11,96],"(SV)":[12],"systems":[13,20],"is":[14,39],"utmost":[16],"importance.":[17],"However,":[18],"SV":[19,64],"are":[21],"inherently":[22],"vulnerable":[23],"to":[24,48,63,80,100,127,175],"various":[25,55],"types":[26],"attacks":[28],"that":[29,190],"can":[30],"compromise":[31],"their":[32],"accuracy":[33],"and":[34],"reliability.":[35],"One":[36],"such":[37],"attack":[38],"voice":[40,98],"conversion":[41,99],"(VC),":[42],"which":[43],"modifies":[44],"person\u2019s":[46],"speech":[47,88,105],"sound":[49],"like":[50],"another":[51],"person":[52],"by":[53],"altering":[54],"vocal":[56],"characteristics.":[57],"This":[58,155],"poses":[59],"significant":[61],"threat":[62],"systems.":[65],"To":[66,137],"address":[67],"this":[68,114],"challenge,":[69],"Source":[71],"Speaker":[72],"Tracing":[73],"Challenge":[74],"(SSTC)":[75],"in":[76,86,134,184,211],"IEEE":[77],"SLT2024":[78],"aims":[79],"identify":[81,160],"source":[83,94,111,124,131,163,180],"information":[85,133,182],"manipulated":[87],"signals.":[89],"Specifically,":[90],"SSTC":[91],"focuses":[92],"on":[93,203],"against":[97],"determine":[101],"whether":[102],"two":[103],"converted":[104,135,186],"samples":[106],"originate":[107],"from":[108],"same":[110],"speaker.":[112],"In":[113],"study,":[115],"we":[116,143],"propose":[117],"contrastive":[120,146,157,194],"learning-based":[121],"approach":[122],"for":[123],"tracing":[126],"learn":[128,138,176],"latent":[130],"speech.":[136,187],"more":[140],"source-speaker-related":[141],"representation,":[142],"employ":[144],"loss":[147,158],"during":[148],"training":[150],"embedding":[153,165,173],"extractor.":[154],"helps":[159],"true":[162],"among":[166],"several":[167],"distractor":[168],"embeddings,":[170],"enabling":[171],"extractor":[174],"potentially":[178],"possessing":[179],"present":[183],"Experiments":[188],"demonstrate":[189],"our":[191],"proposed":[192],"learning":[195],"system":[196],"achieves":[197],"lowest":[199],"EER":[200],"16.788%":[202],"challenge":[205],"test":[206],"set,":[207],"securing":[208],"first":[209],"place":[210],"challenge.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}