{"id":"https://openalex.org/W7148567400","doi":"https://doi.org/10.1109/asru65441.2025.11434771","title":"Towards Generalized Source Tracing for Codec-Based Deepfake Speech","display_name":"Towards Generalized Source Tracing for Codec-Based Deepfake Speech","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148567400","doi":"https://doi.org/10.1109/asru65441.2025.11434771"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5106488141","display_name":"I-Ming Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"I-Ming Lin","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793356","display_name":"Xuanjun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xuanjun Chen","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351902","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0003-0018-3903"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132799449","display_name":"Haibin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["Independent Researcher"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communications Engineering, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communications Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120398738","display_name":"Jyh-Shing Roger Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Department of Computer Science and Information Engineering"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5106488141"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75422833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3634999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3634999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2741999924182892,"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":0.07859999686479568,"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/tracing","display_name":"Tracing","score":0.4361000061035156},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26649999618530273},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.25429999828338623},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.23469999432563782},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.23100000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705999732017517},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37439998984336853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2791999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.23469999432563782},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23100000619888306},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2273000031709671}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":33,"referenced_works":["https://openalex.org/W2176804518","https://openalex.org/W2745896134","https://openalex.org/W2936802426","https://openalex.org/W3157576687","https://openalex.org/W3198486673","https://openalex.org/W3201773091","https://openalex.org/W3211424380","https://openalex.org/W3213029956","https://openalex.org/W4221138880","https://openalex.org/W4225297350","https://openalex.org/W4225527248","https://openalex.org/W4292957223","https://openalex.org/W4312120800","https://openalex.org/W4313156423","https://openalex.org/W4319862411","https://openalex.org/W4381198892","https://openalex.org/W4385245566","https://openalex.org/W4385823150","https://openalex.org/W4385975857","https://openalex.org/W4392909516","https://openalex.org/W4402111541","https://openalex.org/W4402111622","https://openalex.org/W4402111655","https://openalex.org/W4402116004","https://openalex.org/W4402670057","https://openalex.org/W4403955716","https://openalex.org/W4404823409","https://openalex.org/W4406461488","https://openalex.org/W4406803348","https://openalex.org/W4415433255","https://openalex.org/W4415433289","https://openalex.org/W4415433673","https://openalex.org/W4417305271"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"attempts":[1],"at":[2],"source":[3,27,118],"tracing":[4,28],"for":[5,87,95,116],"codecbased":[6],"deepfake":[7],"speech":[8,15],"(CodecFake),":[9],"generated":[10],"by":[11],"neural":[12],"audio":[13,41],"codec-based":[14],"generation":[16],"(CoSG)":[17],"models,":[18],"have":[19],"exhibited":[20],"suboptimal":[21],"performance.":[22],"However,":[23],"how":[24],"to":[25,59,61,66,68],"train":[26],"models":[29,52],"using":[30],"simulated":[31],"CoSG":[32,107],"data":[33,57],"while":[34],"maintaining":[35],"strong":[36],"performance":[37,104],"on":[38,55,105],"real":[39],"CoSG-generated":[40],"remains":[42],"an":[43],"open":[44],"challenge.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,75],"show":[50],"that":[51],"trained":[53],"solely":[54],"codec-resynthesized":[56],"tend":[58],"overfit":[60],"non-speech":[62],"regions":[63],"and":[64,91],"struggle":[65],"generalize":[67],"unseen":[69],"content.":[70],"To":[71],"mitigate":[72],"these":[73],"challenges,":[74],"introduce":[76],"the":[77,106],"Semantic-Acoustic":[78],"Source":[79],"Tracing":[80],"Network":[81],"(SASTNet),":[82],"which":[83],"jointly":[84],"leverages":[85],"Whisper":[86],"semantic":[88],"feature":[89,97],"encoding":[90],"Wav2vec2":[92],"with":[93],"AudioMAE":[94],"acoustic":[96],"encoding.":[98],"Our":[99],"proposed":[100],"SASTNet":[101],"achieves":[102],"state-of-theart":[103],"test":[108],"set":[109],"of":[110],"CodecFake+":[111],"dataset,":[112],"demonstrating":[113],"its":[114],"effectiveness":[115],"reliable":[117],"tracing.":[119]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}