{"id":"https://openalex.org/W4416771681","doi":"https://doi.org/10.1109/sped67700.2025.11252446","title":"Audio Splicing Detection Using Self-Supervised Representations","display_name":"Audio Splicing Detection Using Self-Supervised Representations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771681","doi":"https://doi.org/10.1109/sped67700.2025.11252446"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11252446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5059253663","display_name":"Octavian Pascu","orcid":"https://orcid.org/0000-0003-2643-9145"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Octavian Pascu","raw_affiliation_strings":["POLITEHNICA,Speech and Dialogue Research Laboratory,Bucharest"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA,Speech and Dialogue Research Laboratory,Bucharest","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032257745","display_name":"Horia Cucu","orcid":"https://orcid.org/0000-0002-8711-3854"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Horia Cucu","raw_affiliation_strings":["POLITEHNICA,Speech and Dialogue Research Laboratory,Bucharest"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA,Speech and Dialogue Research Laboratory,Bucharest","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059253663"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40451276,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9775999784469604,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9775999784469604,"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/T11309","display_name":"Music and Audio Processing","score":0.00570000009611249,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/discriminative-model","display_name":"Discriminative model","score":0.6682999730110168},{"id":"https://openalex.org/keywords/rna-splicing","display_name":"RNA splicing","score":0.548799991607666},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48350000381469727},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41749998927116394},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.39480000734329224},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3490999937057495},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3391000032424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361000180244446},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C54458228","wikidata":"https://www.wikidata.org/wiki/Q237218","display_name":"RNA splicing","level":4,"score":0.548799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318999886512756},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41749998927116394},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35030001401901245},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3490999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.29910001158714294}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11252446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2740070353","https://openalex.org/W4226380987","https://openalex.org/W4375869060","https://openalex.org/W4383503745","https://openalex.org/W4385466206","https://openalex.org/W4385822573","https://openalex.org/W4392902854","https://openalex.org/W4393162041","https://openalex.org/W4393228538","https://openalex.org/W4401110595","https://openalex.org/W4402111467","https://openalex.org/W4406267500","https://openalex.org/W4408355324"],"related_works":[],"abstract_inverted_index":{"Audio":[0,35],"splicing":[1,36,72],"is":[2],"the":[3,21,25,43,101,130],"manipulation":[4],"of":[5,23,45],"a":[6,32,66,75,83,110,127],"recording":[7],"by":[8,73,106],"inserting,":[9],"deleting,":[10],"or":[11,18,30,60,95],"rearranging":[12],"segments":[13],"to":[14,57,69,108,137],"alter":[15],"its":[16],"content":[17],"context":[19],"with":[20,82,126],"goal":[22],"misrepresenting":[24],"original":[26],"message,":[27],"fabricating":[28],"evidence,":[29],"creating":[31],"misleading":[33],"narrative.":[34],"detection":[37],"has":[38],"become":[39],"increasingly":[40],"vital":[41],"in":[42,80],"realms":[44],"security,":[46],"digital":[47],"forensics,":[48],"and":[49,118],"fact-checking,":[50],"as":[51],"manipulated":[52],"audio":[53,71,120],"can":[54],"be":[55],"used":[56],"spread":[58],"misinformation":[59],"falsify":[61],"evidence.":[62],"This":[63],"paper":[64],"presents":[65],"novel":[67],"approach":[68],"detecting":[70],"leveraging":[74],"self-supervised":[76],"front":[77],"end,":[78],"wav2vec2,":[79],"combination":[81],"simple":[84],"logistic":[85],"regression":[86],"classifier.":[87],"Unlike":[88],"conventional":[89],"methods":[90],"that":[91,113,124],"require":[92],"handcrafted":[93],"features":[94],"complex":[96],"models,":[97],"our":[98,142],"method":[99],"utilizes":[100],"rich,":[102],"context-aware":[103],"representations":[104,132],"produced":[105],"wav2vec2":[107,131],"train":[109],"linear":[111],"classifier":[112],"effectively":[114],"distinguishes":[115],"between":[116],"authentic":[117],"spliced":[119],"segments.":[121],"We":[122],"demonstrate":[123],"even":[125],"basic":[128],"classifier,":[129],"capture":[133],"sufficient":[134],"discriminative":[135],"information":[136],"achieve":[138],"good":[139],"performance":[140],"on":[141],"benchmark":[143],"dataset.":[144]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}