{"id":"https://openalex.org/W4372348948","doi":"https://doi.org/10.1109/icassp49357.2023.10095653","title":"Pop2Piano : Pop Audio-Based Piano Cover Generation","display_name":"Pop2Piano : Pop Audio-Based Piano Cover Generation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348948","doi":"https://doi.org/10.1109/icassp49357.2023.10095653"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102496283","display_name":"Jong-Ho Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156097","display_name":"Rebellion (United Kingdom)","ror":"https://ror.org/04ppn0b98","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210156097"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jongho Choi","raw_affiliation_strings":["Rebellions Inc"],"affiliations":[{"raw_affiliation_string":"Rebellions Inc","institution_ids":["https://openalex.org/I4210156097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084429729","display_name":"Kyogu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156097","display_name":"Rebellion (United Kingdom)","ror":"https://ror.org/04ppn0b98","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210156097"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Rebellions Inc"],"affiliations":[{"raw_affiliation_string":"Rebellions Inc","institution_ids":["https://openalex.org/I4210156097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102496283"],"corresponding_institution_ids":["https://openalex.org/I4210156097"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70169619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":1.0,"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":1.0,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.9493190050125122},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.7363641262054443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715056300163269},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6054860949516296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5559094548225403},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4885011911392212},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48508420586586},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4459006190299988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2938513159751892},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20630112290382385},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12631219625473022},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11816748976707458}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.9493190050125122},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7363641262054443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715056300163269},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6054860949516296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5559094548225403},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4885011911392212},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48508420586586},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4459006190299988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2938513159751892},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20630112290382385},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12631219625473022},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11816748976707458},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"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":32,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2118774185","https://openalex.org/W2130458498","https://openalex.org/W2903916098","https://openalex.org/W2950547518","https://openalex.org/W2952823162","https://openalex.org/W2998490864","https://openalex.org/W3015213533","https://openalex.org/W3037149862","https://openalex.org/W3049247973","https://openalex.org/W3080857286","https://openalex.org/W3197905771","https://openalex.org/W3209419355","https://openalex.org/W4287072584","https://openalex.org/W4287995946","https://openalex.org/W4288089799","https://openalex.org/W4293775315","https://openalex.org/W4322615164","https://openalex.org/W6712764700","https://openalex.org/W6714030504","https://openalex.org/W6745851314","https://openalex.org/W6746168993","https://openalex.org/W6748326514","https://openalex.org/W6751104502","https://openalex.org/W6755182157","https://openalex.org/W6756669892","https://openalex.org/W6764408361","https://openalex.org/W6769627184","https://openalex.org/W6771747371","https://openalex.org/W6781910838","https://openalex.org/W6798855526","https://openalex.org/W6803088475"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2336023324","https://openalex.org/W633023889"],"abstract_inverted_index":{"Piano":[0,34,68],"covers":[1,17,88],"of":[2,13,18,31,54,63,91,97,131],"pop":[3,19,92,112],"music":[4,20],"are":[5],"enjoyed":[6],"by":[7],"many":[8],"people.":[9],"However,":[10],"the":[11,29,44,52,55,95,102],"task":[12],"automatically":[14],"generating":[15],"piano":[16,87,108,134],"is":[21,25,101,129],"still":[22],"understudied.":[23],"This":[24],"partly":[26],"due":[27],"to":[28,42,105],"lack":[30],"synchronized":[32,66],"{Pop,":[33,67],"Cover}":[35],"data":[36,71],"pairs,":[37],"which":[38],"made":[39],"it":[40],"challenging":[41],"apply":[43],"latest":[45],"data-intensive":[46],"deep":[47],"learning-based":[48],"methods.":[49],"To":[50,94],"leverage":[51],"power":[53],"data-driven":[56],"approach,":[57],"we":[58,79],"make":[59],"a":[60,82,107],"large":[61],"amount":[62],"paired":[64],"and":[65,117],"Cover":[69],"}":[70],"using":[72,115],"an":[73],"automated":[74],"pipeline.":[75],"In":[76],"this":[77,100],"paper,":[78],"present":[80],"Pop2Piano,":[81,124],"Transformer":[83],"network":[84],"that":[85,123],"generates":[86],"given":[89],"waveforms":[90],"music.":[93],"best":[96],"our":[98,127],"knowledge,":[99],"first":[103],"model":[104],"generate":[106],"cover":[109],"directly":[110],"from":[111],"audio":[113],"without":[114],"melody":[116],"chord":[118],"extraction":[119],"modules.":[120],"We":[121],"show":[122],"trained":[125],"with":[126],"dataset,":[128],"capable":[130],"producing":[132],"plausible":[133],"covers.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
