{"id":"https://openalex.org/W4406495739","doi":"https://doi.org/10.1109/bigdata62323.2024.10825221","title":"Diffusion Models for Automatic Music Mixing","display_name":"Diffusion Models for Automatic Music Mixing","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406495739","doi":"https://doi.org/10.1109/bigdata62323.2024.10825221"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5038256245","display_name":"Xinyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xinyang Wu","raw_affiliation_strings":["Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056541447","display_name":"Andrew Horner","orcid":"https://orcid.org/0000-0002-9795-5190"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Andrew Horner","raw_affiliation_strings":["Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Dept. Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038256245"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29214255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3242","last_page":"3247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T11349","display_name":"Music Technology and Sound Studies","score":0.9998999834060669,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.7697895765304565},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.7087036371231079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6255613565444946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32811135053634644},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09152695536613464}],"concepts":[{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.7697895765304565},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.7087036371231079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255613565444946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32811135053634644},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09152695536613464},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-146745","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-146745","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1481019515","https://openalex.org/W1633347946","https://openalex.org/W1989252926","https://openalex.org/W2074704838","https://openalex.org/W2099520264","https://openalex.org/W2121388655","https://openalex.org/W2158993297","https://openalex.org/W2194775991","https://openalex.org/W2937484199","https://openalex.org/W2963452667","https://openalex.org/W3001377302","https://openalex.org/W3001643781","https://openalex.org/W3024761859","https://openalex.org/W3036167779","https://openalex.org/W3041281612","https://openalex.org/W3099024959","https://openalex.org/W3107734107","https://openalex.org/W3212355666","https://openalex.org/W3213726885","https://openalex.org/W4230685051","https://openalex.org/W4237278435","https://openalex.org/W4245782970","https://openalex.org/W4293169095","https://openalex.org/W4297841790","https://openalex.org/W4313560685","https://openalex.org/W4372260250","https://openalex.org/W4385245566","https://openalex.org/W4387813298","https://openalex.org/W4391901235","https://openalex.org/W4392971695","https://openalex.org/W4398796205","https://openalex.org/W6687483927","https://openalex.org/W6714030504","https://openalex.org/W6751512325","https://openalex.org/W6767879806","https://openalex.org/W6779823529","https://openalex.org/W6785943636","https://openalex.org/W6841440234","https://openalex.org/W6848048183","https://openalex.org/W6861565925","https://openalex.org/W6863989086","https://openalex.org/W6868448943","https://openalex.org/W6941472509"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Music":[0],"mixing":[1,34,121],"is":[2,78],"a":[3],"process":[4,92],"that":[5],"involves":[6],"fine-tuning":[7],"the":[8,23,48,58,71,75,83,89,105,109],"levels,":[9],"dynamics,":[10],"and":[11,20,60,74,111],"frequency":[12,59],"content":[13],"of":[14],"musical":[15],"elements":[16],"to":[17,40,56,86,93],"ensure":[18],"clarity":[19],"harmony":[21],"in":[22,43,65,129],"final":[24],"music":[25,44],"production.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"present":[31],"an":[32,95],"automatic":[33,120],"system":[35],"based":[36],"on":[37],"diffusion":[38,84],"models":[39],"correct":[41],"imbalances":[42,62],"mixes.":[45,113],"We":[46,98],"manipulate":[47],"well":[49],"mixed":[50],"stems\u2019":[51],"short-time":[52],"Fourier":[53],"transform":[54],"randomly":[55],"simulate":[57],"level":[61],"commonly":[63],"encountered":[64],"real-world":[66],"scenarios.":[67],"The":[68],"difference":[69],"between":[70,108],"imbalanced":[72],"mix":[73,77],"original":[76,110],"treated":[79],"as":[80],"noise":[81],"for":[82],"model":[85],"predict,":[87],"enabling":[88],"reverse":[90],"denoising":[91],"generate":[94],"automated":[96],"mix.":[97],"evaluate":[99],"our":[100],"model\u2019s":[101],"performance":[102],"by":[103],"calculating":[104],"signal-to-distortion":[106],"ratio":[107],"predicted":[112],"These":[114],"results":[115,128],"are":[116],"compared":[117],"with":[118],"baseline":[119],"models,":[122],"demonstrating":[123],"significant":[124],"improvements.":[125],"Test":[126],"set":[127],"audio:":[130],"https://aimg2025submission.github.io/diffmusicmix/":[131]},"counts_by_year":[],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
