{"id":"https://openalex.org/W6912022557","doi":"https://doi.org/10.5281/zenodo.14877397","title":"PiCoGen2: Piano Cover Generation With Transfer Learning Approach and Weakly Aligned Data","display_name":"PiCoGen2: Piano Cover Generation With Transfer Learning Approach and Weakly Aligned Data","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6912022557","doi":"https://doi.org/10.5281/zenodo.14877397"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877397","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877397","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chih-Pin Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chih-Pin Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hsin Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin Ai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yi-Hsin Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Hsin Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shuen-Huei Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuen-Huei Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yi-Hsuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0,"citation_normalized_percentile":null,"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/T12445","display_name":"Twentieth Century Scientific Developments","score":0.10570000112056732,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12445","display_name":"Twentieth Century Scientific Developments","score":0.10570000112056732,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"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/T13297","display_name":"History and advancements in chemistry","score":0.07289999723434448,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12337","display_name":"Italian Fascism and Post-war Society","score":0.06239999830722809,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.9319999814033508},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.604200005531311},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5602999925613403},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47850000858306885},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.9319999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542999744415283},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4706999957561493},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40130001306533813},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877397","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877397","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877397","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877397","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":"ConferencePaper"},"sustainable_development_goals":[{"score":0.4989440143108368,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Piano":[0],"cover":[1,8],"generation":[2],"aims":[3],"to":[4,35,89,93,114,133,139,156],"create":[5],"a":[6,10,65],"piano":[7,33,46,57,95,120],"from":[9,118],"pop":[11,141,170],"song.":[12],"Existing":[13],"approaches":[14],"mainly":[15],"employ":[16],"supervised":[17],"learning":[18,67],"and":[19,24,48,55,76,165],"the":[20,43,53,91,112,119,129,135,140],"training":[21,149],"demands":[22],"strongly-aligned":[23],"paired":[25,81,130],"song-to-piano":[26],"data,":[27],"which":[28],"is":[29,125],"built":[30],"by":[31],"remapping":[32],"notes":[34],"song":[36,142],"audio.":[37],"This":[38],"would,":[39],"however,":[40],"result":[41],"in":[42],"loss":[44],"of":[45,99],"information":[47],"accordingly":[49],"cause":[50],"inconsistencies":[51],"between":[52],"original":[54],"remapped":[56],"versions.":[58],"To":[59],"overcome":[60],"this":[61,148],"limitation,":[62],"we":[63,103],"propose":[64],"transfer":[66,134],"approach":[68],"that":[69,147],"pre-trains":[70],"our":[71,152],"model":[72,92,110,124],"on":[73,79,128,162],"piano-only":[74],"data":[75,82,132],"fine-tunes":[77],"it":[78],"weakly-aligned":[80],"constructed":[83],"without":[84],"note":[85],"remapping.":[86],"During":[87],"pre-training,":[88],"guide":[90],"learn":[94],"composition":[96,137],"concepts":[97],"instead":[98],"merely":[100],"transcribing":[101],"audio,":[102],"use":[104],"an":[105],"existing":[106],"lead":[107],"sheet":[108],"transcription":[109],"as":[111],"encoder":[113],"extract":[115],"high-level":[116],"features":[117],"recordings.":[121],"The":[122],"pre-trained":[123],"then":[126],"fine-tuned":[127],"song-piano":[131],"learned":[136],"knowledge":[138],"domain.":[143],"Our":[144],"evaluation":[145],"shows":[146],"strategy":[150],"enables":[151],"model,":[153],"named":[154],"PiCoGen2,":[155],"attain":[157],"high-quality":[158],"results,":[159],"outperforming":[160],"baselines":[161],"both":[163],"objective":[164],"subjective":[166],"metrics":[167],"across":[168],"five":[169],"genres.":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}