{"id":"https://openalex.org/W4372263680","doi":"https://doi.org/10.1109/icassp49357.2023.10096458","title":"Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects","display_name":"Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263680","doi":"https://doi.org/10.1109/icassp49357.2023.10096458"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096458","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/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"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"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Department of Intelligence and Information, Music and Audio Research Group, Seoul National University","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Intelligence and Information, Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017282176","display_name":"Marco A. Mart\u00ednez-Ram\u00edrez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco A. Mart\u00ednez-Ram\u00edrez","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010554448","display_name":"Stefan Uhlich","orcid":"https://orcid.org/0000-0003-3158-4945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Uhlich","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany","Sony Europe B.V., Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]},{"raw_affiliation_string":"Sony Europe B.V., Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081140658","display_name":"Kyogu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]},{"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"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group,Department of Intelligence and Information","Department of Intelligence and Information, Music and Audio Research Group, Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group,Department of Intelligence and Information","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Department of Intelligence and Information, Music and Audio Research Group, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031164776"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":2.8946,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91757147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7023962736129761},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.6857157945632935},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.671727180480957},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6536983847618103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6204017400741577},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5703088641166687},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5435599684715271},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5192763805389404},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4814795255661011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4720260202884674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3697812557220459},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.21888044476509094},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.19230982661247253},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07469195127487183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023962736129761},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6857157945632935},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.671727180480957},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6536983847618103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6204017400741577},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5703088641166687},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5435599684715271},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5192763805389404},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4814795255661011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4720260202884674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3697812557220459},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.21888044476509094},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.19230982661247253},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07469195127487183},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096458","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":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2581073931","https://openalex.org/W2760103357","https://openalex.org/W2785961484","https://openalex.org/W2963263347","https://openalex.org/W2975549126","https://openalex.org/W2979770961","https://openalex.org/W2993093732","https://openalex.org/W3000389243","https://openalex.org/W3005680577","https://openalex.org/W3112497262","https://openalex.org/W3139211892","https://openalex.org/W3162289111","https://openalex.org/W3163735648","https://openalex.org/W3165004824","https://openalex.org/W3199957557","https://openalex.org/W3205065023","https://openalex.org/W3213726885","https://openalex.org/W4226175735","https://openalex.org/W4226300471","https://openalex.org/W4287329493","https://openalex.org/W4298310324","https://openalex.org/W4307977691","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6732251933","https://openalex.org/W6748445624","https://openalex.org/W6766320909","https://openalex.org/W6768496761","https://openalex.org/W6771763809","https://openalex.org/W6774314701","https://openalex.org/W6791537541","https://openalex.org/W6801090061","https://openalex.org/W6802387851","https://openalex.org/W6840348479"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"We":[0,78],"propose":[1],"an":[2,15,28,57,63],"end-to-end":[3],"music":[4,45,137],"mixing":[5,12,96,117],"style":[6,13,97,118,132],"transfer":[7,98,133],"system":[8,112],"that":[9,19,68],"converts":[10,115],"the":[11,70,80,84,106,110,116],"of":[14,20,73,87,119],"input":[16],"multitrack":[17,60,120],"to":[18,35,123],"a":[21,32,43,53,124,136],"reference":[22,44,125],"song.":[23],"This":[24],"is":[25,127],"achieved":[26],"with":[27,31,62,130],"encoder":[29,82],"pre-trained":[30],"contrastive":[33],"objective":[34,101],"extract":[36],"only":[37,114],"audio":[38,88,121],"effects":[39,89],"related":[40],"information":[41],"from":[42,56],"recording.":[46],"All":[47],"our":[48],"models":[49],"are":[50],"trained":[51],"in":[52],"self-supervised":[54],"manner":[55],"already-processed":[58],"wet":[59],"dataset":[61],"effective":[64],"data":[65,71],"preprocessing":[66],"method":[67],"alleviates":[69],"scarcity":[72],"obtaining":[74],"unprocessed":[75],"dry":[76],"data.":[77],"analyze":[79],"proposed":[81,111],"for":[83,95],"disentanglement":[85],"capability":[86],"and":[90,102],"also":[91,128],"validate":[92],"its":[93],"performance":[94],"through":[99],"both":[100],"subjective":[103],"evaluations.":[104],"From":[105],"results,":[107],"we":[108],"show":[109],"not":[113],"close":[122],"but":[126],"robust":[129],"mixture-wise":[131],"upon":[134],"using":[135],"source":[138],"separation":[139],"model.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}