{"id":"https://openalex.org/W4226175735","doi":"https://doi.org/10.1109/icassp43922.2022.9746389","title":"End-To-End Music Remastering System Using Self-Supervised And Adversarial Training","display_name":"End-To-End Music Remastering System Using Self-Supervised And Adversarial Training","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226175735","doi":"https://doi.org/10.1109/icassp43922.2022.9746389"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746389","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Music and Audio Research Group,Department of Intelligence and Information","Department of Intelligence and Information, Music and Audio Research Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]},{"raw_affiliation_string":"Department of Intelligence and Information, Music and Audio Research Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035078120","display_name":"Seungryeol Paik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungryeol Paik","raw_affiliation_strings":["Music and Audio Research Group,Department of Intelligence and Information","Department of Intelligence and Information, Music and Audio Research Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]},{"raw_affiliation_string":"Department of Intelligence and Information, Music and Audio Research Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Music and Audio Research Group,Department of Intelligence and Information","AI Institute","Department of Intelligence and Information, Music and Audio Research Group","Graduate School of AI, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Group,Department of Intelligence and Information","institution_ids":[]},{"raw_affiliation_string":"AI Institute","institution_ids":["https://openalex.org/I2799847335"]},{"raw_affiliation_string":"Department of Intelligence and Information, Music and Audio Research Group","institution_ids":[]},{"raw_affiliation_string":"Graduate School of AI, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6472,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77728131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4608","last_page":"4612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9976000189781189,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9860000014305115,"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/T11309","display_name":"Music and Audio Processing","score":0.9700999855995178,"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/adversarial-system","display_name":"Adversarial system","score":0.7997657060623169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7237146496772766},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7074702382087708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42430949211120605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42227429151535034},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4107989966869354}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7997657060623169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7237146496772766},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7074702382087708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42430949211120605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42227429151535034},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4107989966869354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746389","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W118467652","https://openalex.org/W1522301498","https://openalex.org/W1525353496","https://openalex.org/W1998648683","https://openalex.org/W2067295501","https://openalex.org/W2121044470","https://openalex.org/W2194775991","https://openalex.org/W2507109542","https://openalex.org/W2754165686","https://openalex.org/W2760103357","https://openalex.org/W2787579267","https://openalex.org/W2791686384","https://openalex.org/W2887323116","https://openalex.org/W2898469868","https://openalex.org/W2899388747","https://openalex.org/W2950060770","https://openalex.org/W2963452667","https://openalex.org/W3000389243","https://openalex.org/W3005680577","https://openalex.org/W3015580115","https://openalex.org/W3139211892","https://openalex.org/W3162289111","https://openalex.org/W3163547199","https://openalex.org/W3163735648","https://openalex.org/W3174807077","https://openalex.org/W6604789010","https://openalex.org/W6631190155","https://openalex.org/W6631587439","https://openalex.org/W6678230397","https://openalex.org/W6748655329","https://openalex.org/W6751512325","https://openalex.org/W6763945542","https://openalex.org/W6771763809","https://openalex.org/W6772157574","https://openalex.org/W6774314701","https://openalex.org/W6779841522","https://openalex.org/W6791537541","https://openalex.org/W6797179183"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Mastering":[0],"is":[1,10,89],"an":[2,69],"essential":[3],"step":[4],"in":[5,42,47,91,95],"music":[6,71],"production,":[7],"but":[8],"it":[9],"also":[11,105],"a":[12,34,49,92,120,124,135],"challenging":[13],"task":[14],"that":[15,74,83,141],"has":[16],"to":[17,63,82,109,150],"go":[18],"through":[19],"the":[20,38,44,52,65,76,85,107,114,142,151],"hands":[21],"of":[22,33,79,84,146],"experienced":[23],"audio":[24,81,112],"engineers,":[25],"where":[26],"they":[27],"adjust":[28],"tone,":[29],"space,":[30],"and":[31,123,134,139],"volume":[32],"song.":[35],"Remastering":[36],"follows":[37],"same":[39],"technical":[40],"process,":[41],"which":[43,96],"context":[45],"lies":[46],"mastering":[48,77,116,147],"song":[50],"for":[51,102],"times.":[53],"As":[54],"these":[55],"tasks":[56],"have":[57],"high":[58],"entry":[59],"barriers,":[60],"we":[61],"aim":[62],"lower":[64],"barriers":[66],"by":[67,118],"proposing":[68],"end-to-end":[70],"remastering":[72],"system":[73,88],"transforms":[75],"style":[78,117,148],"input":[80],"target.":[86,152],"The":[87],"trained":[90],"self-supervised":[93],"manner,":[94],"released":[97],"pop":[98],"songs":[99],"were":[100],"used":[101],"training.":[103],"We":[104,127],"anticipated":[106],"model":[108,143],"generate":[110],"realistic":[111],"reflecting":[113],"reference\u2019s":[115],"applying":[119],"pre-trained":[121],"encoder":[122],"projection":[125],"discriminator.":[126],"validate":[128],"our":[129],"results":[130],"with":[131],"quantitative":[132],"metrics":[133],"subjective":[136],"listening":[137],"test":[138],"show":[140],"generated":[144],"samples":[145],"similar":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}