{"id":"https://openalex.org/W4406461836","doi":"https://doi.org/10.1109/slt61566.2024.10832322","title":"Integrating Self-Supervised Pre-Training With Adversarial Learning for Synthesized Song Detection","display_name":"Integrating Self-Supervised Pre-Training With Adversarial Learning for Synthesized Song Detection","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461836","doi":"https://doi.org/10.1109/slt61566.2024.10832322"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832322","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":"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/A5101542883","display_name":"Yankai Wang","orcid":"https://orcid.org/0009-0000-9240-5459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yankai Wang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011431550","display_name":"Yuxuan Du","orcid":"https://orcid.org/0000-0002-5997-7882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Du","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064727229","display_name":"Dejun Zhang","orcid":"https://orcid.org/0000-0001-9129-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejun Zhang","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056442083","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0003-4070-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":["Beijing Fosafer Information Technology Co., Ltd,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Fosafer Information Technology Co., Ltd,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68478604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"795","last_page":"802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/adversarial-system","display_name":"Adversarial system","score":0.8098069429397583},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7467618584632874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6415958404541016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418491959571838},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5380894541740417},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.450141042470932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4391222298145294}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8098069429397583},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7467618584632874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6415958404541016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418491959571838},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5380894541740417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450141042470932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4391222298145294},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832322","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2014485509","https://openalex.org/W2112606109","https://openalex.org/W2303197844","https://openalex.org/W2763881998","https://openalex.org/W2913181996","https://openalex.org/W2991187463","https://openalex.org/W3151295995","https://openalex.org/W3158762648","https://openalex.org/W3160325739","https://openalex.org/W3161011913","https://openalex.org/W3170179936","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3200167423","https://openalex.org/W3201197228","https://openalex.org/W3201773091","https://openalex.org/W3212117663","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4285149944","https://openalex.org/W4296068826","https://openalex.org/W4297841768","https://openalex.org/W4372260253","https://openalex.org/W4372342398","https://openalex.org/W4375868770","https://openalex.org/W4378506723","https://openalex.org/W4385823150","https://openalex.org/W4387665604","https://openalex.org/W4389914235","https://openalex.org/W4390479001","https://openalex.org/W4390691474","https://openalex.org/W4391021548","https://openalex.org/W4392270819","https://openalex.org/W4392903644","https://openalex.org/W4392908976","https://openalex.org/W4392931459","https://openalex.org/W4401609106","https://openalex.org/W4402111617","https://openalex.org/W6798697749","https://openalex.org/W6852755086","https://openalex.org/W6862259629","https://openalex.org/W6891819772"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Existing":[0],"spoofing":[1],"detection":[2],"systems":[3],"often":[4],"perform":[5],"poorly":[6],"when":[7],"applied":[8],"to":[9,34,52,73,76,123],"highly":[10],"realistic":[11],"synthetic":[12],"song":[13],"datasets.":[14],"To":[15],"address":[16],"it,":[17],"we":[18,30,58],"propose":[19],"a":[20,43,60,65],"method":[21],"that":[22,94],"integrates":[23],"self-supervised":[24],"pre-training":[25],"with":[26],"adversarial":[27,71],"learning.":[28],"Initially,":[29],"utilize":[31],"wav2vec":[32],"2.0":[33],"extract":[35],"audio":[36,55],"representations,":[37],"which":[38],"are":[39,85],"subsequently":[40],"fed":[41],"into":[42],"back-end":[44],"classifier.":[45],"A":[46],"ResBlock-based":[47],"network":[48],"is":[49],"then":[50],"employed":[51],"capture":[53],"fine-grained":[54],"features.":[56],"Additionally,":[57],"enhance":[59],"RawNet-based":[61],"model":[62],"by":[63],"incorporating":[64],"gradient":[66],"reversal":[67],"layer":[68],"and":[69],"applying":[70],"training":[72],"improve":[74],"generalization":[75],"unknown":[77],"algorithms.":[78],"Finally,":[79],"the":[80,88,105,109,124,130,134],"outputs":[81],"of":[82,102,108,120,137],"various":[83],"models":[84],"combined":[86],"at":[87],"score":[89],"level.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"our":[95],"approach":[96],"achieves":[97,129],"Equal":[98],"Error":[99],"Rates":[100],"(EER)":[101],"1.57%":[103],"on":[104],"test":[106],"sets":[107],"Controlled":[110],"Singing":[111],"Voice":[112],"Deepfake":[113],"Detection":[114],"(CtrSVDD)":[115],"track,":[116],"providing":[117],"relative":[118],"reductions":[119],"84.89%":[121],"compared":[122],"baseline":[125],"B02.":[126],"Our":[127],"system":[128],"first":[131],"place":[132],"during":[133],"CtrSVDD":[135],"track":[136],"SVDD":[138],"challenge":[139],"2024.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}