{"id":"https://openalex.org/W7108726552","doi":"https://doi.org/10.5281/zenodo.17811335","title":"ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors","display_name":"ITO-Master: Inference-Time Optimization for Audio Effects Modeling of Music Mastering Processors","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108726552","doi":"https://doi.org/10.5281/zenodo.17811335"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811335","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811335","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junghyun Koo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Marco Martinez-Ramirez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Martinez-Ramirez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"WeiHsiang Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"WeiHsiang Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Giorgio Fabbro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgio Fabbro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Michele Mancusi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Mancusi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yuki Mitsufuji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53798537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.4041000008583069,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.4041000008583069,"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":0.22769999504089355,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15929999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4952999949455261},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4724000096321106},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.43700000643730164},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.40700000524520874},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38749998807907104},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519999742507935},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4318999946117401},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C8854915","wikidata":"https://www.wikidata.org/wiki/Q4350200","display_name":"Information transfer","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811335","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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811335","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":""},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.637722373008728,"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":{"Music":[0],"mastering":[1,10,23,57,73,98,109,116,141,157],"style":[2,58,142,158,169],"transfer":[3,59],"aims":[4],"to":[5,16,39,43,66,86,94,162],"model":[6],"and":[7,104,111,127,153],"apply":[8,28],"the":[9,21,41,52,72,77,88,167],"characteristics":[11],"of":[12],"a":[13,17,33,55],"reference":[14,34,78],"track":[15],"target":[18],"track,":[19,35],"simulating":[20],"professional":[22],"process.":[24,74],"However,":[25],"existing":[26],"methods":[27,106],"fixed":[29],"processing":[30],"based":[31],"on":[32],"limiting":[36],"users'":[37],"ability":[38],"fine-tune":[40],"results":[42,165],"match":[44],"their":[45,164],"artistic":[46],"intent.In":[47],"this":[48],"paper,":[49],"we":[50,136],"introduce":[51],"ITO-Master":[53],"framework,":[54],"reference-based":[56],"system":[60],"that":[61,113,138],"integrates":[62],"Inference-Time":[63],"Optimization":[64],"(ITO)":[65],"enable":[67],"finer":[68],"user":[69],"control":[70],"over":[71],"By":[75],"optimizing":[76],"embedding":[79],"during":[80],"inference,":[81],"our":[82],"approach":[83],"allows":[84],"users":[85,161],"refine":[87,163],"output":[89],"dynamically,":[90],"making":[91],"micro-level":[92],"adjustments":[93],"achieve":[95],"more":[96],"precise":[97],"results.":[99],"We":[100],"explore":[101],"both":[102],"black-box":[103],"white-box":[105],"for":[107,156],"modeling":[108],"processors":[110],"demonstrate":[112],"ITO":[114,139],"improves":[115],"performance":[117],"across":[118],"different":[119],"styles.":[120],"Through":[121],"objective":[122],"evaluation,":[123],"subjective":[124],"listening":[125],"tests,":[126],"qualitative":[128],"analysis":[129],"using":[130],"text-based":[131],"conditioning":[132],"with":[133],"CLAP":[134],"embeddings,":[135],"validate":[137],"enhances":[140],"similarity":[143],"while":[144],"offering":[145],"increased":[146],"adaptability.":[147],"Our":[148],"framework":[149],"provides":[150],"an":[151],"effective":[152],"user-controllable":[154],"solution":[155],"transfer,":[159],"allowing":[160],"beyond":[166],"initial":[168],"transfer.":[170]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-05T00:00:00"}