{"id":"https://openalex.org/W4416799996","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249059","title":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","display_name":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799996","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249059"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249059","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/A5101467550","display_name":"Yumin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105315","display_name":"Moscow Institute of Entrepreneurship and Law","ror":"https://ror.org/01q2ngy08","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210105315"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yumin Kim","raw_affiliation_strings":["MIPPIA Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIPPIA Inc","institution_ids":["https://openalex.org/I4210105315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008674254","display_name":"Seonghyeon Go","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105315","display_name":"Moscow Institute of Entrepreneurship and Law","ror":"https://ror.org/01q2ngy08","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210105315"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Seonghyeon Go","raw_affiliation_strings":["MIPPIA Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIPPIA Inc","institution_ids":["https://openalex.org/I4210105315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210105315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38822164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"664","last_page":"669"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9803000092506409,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9803000092506409,"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/T13996","display_name":"Diverse Musicological Studies","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.0008999999845400453,"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/music-information-retrieval","display_name":"Music information retrieval","score":0.7056999802589417},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4675000011920929},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4577000141143799},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.38019999861717224},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3691999912261963},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3393999934196472}],"concepts":[{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.7056999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703499972820282},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5856000185012817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.38019999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27790001034736633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2632000148296356},{"id":"https://openalex.org/C206118826","wikidata":"https://www.wikidata.org/wiki/Q3841682","display_name":"Multiple signal classification","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249059","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2038452924","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2991318208","https://openalex.org/W3135809943","https://openalex.org/W3160525311","https://openalex.org/W3198529186","https://openalex.org/W3209546571","https://openalex.org/W3212117663","https://openalex.org/W4225527248","https://openalex.org/W4312443924","https://openalex.org/W4372263680","https://openalex.org/W4381198892","https://openalex.org/W4389633690","https://openalex.org/W4390874070","https://openalex.org/W4392560653","https://openalex.org/W4392903114","https://openalex.org/W4396877837","https://openalex.org/W4408345930","https://openalex.org/W4412653550"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"and":[1,27,119,127,137,159],"music":[2,11,31,73,116],"generation":[3],"systems":[4],"have":[5],"been":[6],"remarkably":[7],"developed":[8,110],"in":[9,133],"the":[10,62,69,125,135,157],"information":[12],"retrieval":[13],"(MIR)":[14],"research":[15],"field.":[16],"The":[17],"advancement":[18],"of":[19,29,64,72,161],"these":[20,56],"technologies":[21],"raises":[22],"copyright":[23],"concerns,":[24],"as":[25],"ownership":[26],"authorship":[28],"AI-generated":[30],"(AIGM)":[32],"remain":[33],"unclear.":[34],"Also,":[35],"it":[36],"can":[37,153],"be":[38],"difficult":[39],"to":[40,60,76],"determine":[41],"whether":[42],"a":[43,111],"piece":[44],"was":[45],"generated":[46],"by":[47,51,67],"AI":[48],"or":[49,94],"composed":[50],"humans":[52],"clearly.":[53],"To":[54],"address":[55],"challenges,":[57],"we":[58,84,109],"aim":[59],"improve":[61],"accuracy":[63,132],"AIGM":[65,162],"detection":[66,139,163],"analyzing":[68],"structural":[70],"patterns":[71],"segments.":[74],"Specifically,":[75],"extract":[77],"musical":[78,147],"features":[79,148],"from":[80],"short":[81],"audio":[82,96],"clips,":[83],"integrated":[85],"various":[86],"pre-trained":[87],"models,":[88],"including":[89],"self-supervised":[90],"learning":[91],"(SSL)":[92],"models":[93],"an":[95],"effect":[97],"encoder,":[98],"each":[99],"within":[100],"our":[101],"suggested":[102],"transformerbased":[103],"framework.":[104],"Furthermore,":[105],"for":[106],"long":[107],"audio,":[108],"segment":[112],"transformer":[113],"that":[114,144],"divides":[115],"into":[117,149],"segments":[118],"learns":[120],"inter-segment":[121],"relationships.":[122],"We":[123],"used":[124],"FakeMusicCaps":[126],"SONICS":[128],"datasets,":[129],"achieving":[130],"high":[131],"both":[134,156],"short-audio":[136],"full-audio":[138],"experiments.":[140],"These":[141],"findings":[142],"suggest":[143],"integrating":[145],"segment-level":[146],"long-range":[150],"temporal":[151],"analysis":[152],"effectively":[154],"enhance":[155],"performance":[158],"robustness":[160],"systems.":[164]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}