{"id":"https://openalex.org/W6968059051","doi":"https://doi.org/10.5281/zenodo.14877345","title":"Efficient Adapter Tuning for Joint Singing Voice Beat and Downbeat Tracking With Self-Supervised Learning Features","display_name":"Efficient Adapter Tuning for Joint Singing Voice Beat and Downbeat Tracking With Self-Supervised Learning Features","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968059051","doi":"https://doi.org/10.5281/zenodo.14877345"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877345","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiajun Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yaolong Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaolong Ju","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Simon Lui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Lui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xunying Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44833494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5339999794960022,"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":0.5339999794960022,"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/T10863","display_name":"Voice and Speech Disorders","score":0.18809999525547028,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.11990000307559967,"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/beat","display_name":"Beat (acoustics)","score":0.7249000072479248},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6601999998092651},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5917999744415283},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4595000147819519},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2847000062465668}],"concepts":[{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.7249000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010999917984009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6822999715805054},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6601999998092651},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.24199999868869781},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23749999701976776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877345","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877345","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877345","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Singing":[0],"voice":[1,105],"beat":[2,26,60,92,152],"tracking":[3,27],"is":[4,55],"a":[5,40],"challenging":[6],"task,":[7],"due":[8],"to":[9,57,73,90,133,144],"the":[10,59,75,86,102,110,124,128,138],"lack":[11],"of":[12,63,78,95,130],"musical":[13],"accompaniment":[14],"that":[15,97,117],"often":[16],"contains":[17],"robust":[18],"rhythmic":[19],"and":[20,30,52,61,81,120,127,146,153],"harmonic":[21],"patterns,":[22],"something":[23],"most":[24],"existing":[25],"systems":[28],"utilize":[29],"can":[31],"be":[32],"essential":[33],"for":[34],"estimating":[35],"beats.":[36],"In":[37],"this":[38],"paper,":[39],"novel":[41],"temporal":[42],"convolutional":[43],"network-based":[44],"beat-tracking":[45],"approach":[46],"featuring":[47],"self-supervised":[48],"learning":[49],"(SSL)":[50],"representations":[51,70],"adapter":[53,112,121],"tuning":[54,122],"proposed":[56],"track":[58],"downbeat":[62,154],"singing":[64,79,104],"voices":[65,80],"jointly.":[66],"The":[67],"SSL":[68],"DistilHuBERT":[69],"are":[71,82,98,107],"utilized":[72],"capture":[74],"semantic":[76],"information":[77],"further":[83],"fused":[84],"with":[85,101,142],"generic":[87],"spectral":[88],"features":[89],"facilitate":[91],"estimation.":[93],"Sources":[94],"variabilities":[96],"particularly":[99],"prominent":[100],"non-homogeneous":[103],"data":[106],"reduced":[108],"by":[109],"efficient":[111],"tuning.":[113],"Extensive":[114],"experiments":[115],"show":[116],"feature":[118],"fusion":[119],"improve":[123],"performance":[125],"individually,":[126],"combination":[129],"both":[131],"leads":[132],"significantly":[134],"better":[135],"performances":[136],"than":[137],"un-adapted":[139],"baseline":[140],"system,":[141],"up":[143],"31.6%":[145],"42.4%":[147],"absolute":[148],"F1-score":[149],"improvements":[150],"on":[151],"tracking,":[155],"respectively.":[156]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}