{"id":"https://openalex.org/W4416250925","doi":"https://doi.org/10.1109/waspaa66052.2025.11231012","title":"Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis","display_name":"Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250925","doi":"https://doi.org/10.1109/waspaa66052.2025.11231012"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11231012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5100635278","display_name":"Yixiao Zhang","orcid":"https://orcid.org/0000-0001-7026-4202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixiao Zhang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767769","display_name":"Haonan Chen","orcid":"https://orcid.org/0000-0001-8885-5051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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":0.9918000102043152,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0031999999191612005,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6240000128746033},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.559499979019165},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5138000249862671},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46709999442100525},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4503999948501587},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.42739999294281006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355999946594238},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6240000128746033},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357000231742859},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5138000249862671},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4503999948501587},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2840000092983246},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11231012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11231012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":18,"referenced_works":["https://openalex.org/W1990259712","https://openalex.org/W2032085270","https://openalex.org/W2051307814","https://openalex.org/W2052872069","https://openalex.org/W2125192846","https://openalex.org/W2168249484","https://openalex.org/W2891780888","https://openalex.org/W2913868053","https://openalex.org/W2963351448","https://openalex.org/W3097777922","https://openalex.org/W3098447809","https://openalex.org/W3162686331","https://openalex.org/W4224944643","https://openalex.org/W4300914774","https://openalex.org/W4309354577","https://openalex.org/W4386763510","https://openalex.org/W4392904213","https://openalex.org/W4413472064"],"related_works":[],"abstract_inverted_index":{"Audio-based":[0],"music":[1,33,75],"structure":[2],"analysis":[3,85],"(MSA)":[4],"is":[5],"an":[6],"essential":[7],"task":[8],"in":[9,89],"Music":[10],"Information":[11],"Retrieval":[12],"that":[13,116],"remains":[14],"challenging":[15],"due":[16],"to":[17,63,79],"the":[18,28,109],"complexity":[19],"and":[20,50,58,103,112,124,133],"variability":[21],"of":[22,30,86],"musical":[23],"form.":[24],"Recent":[25],"advances":[26],"highlight":[27],"potential":[29],"fine-tuning":[31,74],"pre-trained":[32],"foundation":[34,76],"models":[35,41,77],"for":[36,73],"MSA":[37],"tasks.":[38],"However,":[39],"these":[40],"are":[42],"typically":[43],"trained":[44],"with":[45],"high":[46],"temporal":[47,70],"feature":[48],"resolution":[49],"short":[51],"audio":[52,100],"windows,":[53],"which":[54],"limits":[55],"their":[56],"efficiency":[57],"introduces":[59],"bias":[60],"when":[61],"applied":[62],"long-form":[64],"audio.":[65],"This":[66],"paper":[67],"presents":[68],"a":[69,90],"adaptation":[71],"approach":[72],"tailored":[78],"MSA.":[80],"Our":[81],"method":[82,118],"enables":[83],"efficient":[84],"full-length":[87],"songs":[88],"single":[91],"forward":[92],"pass":[93],"by":[94],"incorporating":[95],"two":[96],"key":[97],"strategies:":[98],"(1)":[99],"window":[101],"extension":[102],"(2)":[104],"low-resolution":[105],"adaptation.":[106],"Experiments":[107],"on":[108],"Harmonix":[110],"Set":[111],"RWC-Pop":[113],"datasets":[114],"show":[115],"our":[117],"significantly":[119],"improves":[120],"both":[121],"boundary":[122],"detection":[123],"structural":[125],"function":[126],"prediction,":[127],"while":[128],"maintaining":[129],"comparable":[130],"memory":[131],"usage":[132],"inference":[134],"speed.":[135],"<sup":[136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}