{"id":"https://openalex.org/W6949349252","doi":"https://doi.org/10.5281/zenodo.14877399","title":"Diff-MST: Differentiable Mixing Style Transfer","display_name":"Diff-MST: Differentiable Mixing Style Transfer","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6949349252","doi":"https://doi.org/10.5281/zenodo.14877399"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877399","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877399","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.14877399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Soumya Sai Vanka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Soumya Sai Vanka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Christian J. Steinmetz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian J. Steinmetz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jean-Baptiste Rolland","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Rolland","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Joshua D. Reiss","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joshua D. Reiss","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"George Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.44496174,"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":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5511999726295471,"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":0.5511999726295471,"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":0.1906999945640564,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09220000356435776,"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/interpretability","display_name":"Interpretability","score":0.7626000046730042},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.6746000051498413},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6510999798774719},{"id":"https://openalex.org/keywords/code-mixing","display_name":"Code-mixing","score":0.4832000136375427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7626000046730042},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6746000051498413},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205999851226807},{"id":"https://openalex.org/C2778598016","wikidata":"https://www.wikidata.org/wiki/Q3201279","display_name":"Code-mixing","level":3,"score":0.4832000136375427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31839999556541443},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877399","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877399","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.14877399","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877399","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mixing":[0],"style":[1,29,85,152],"transfer":[2,30],"automates":[3],"the":[4,142,159],"generation":[5],"of":[6,14,43,123,144],"a":[7,11,21,40,71,74,78,93,105],"multi-track":[8],"mix":[9],"for":[10,27,101,158],"given":[12,160],"set":[13],"tracks":[15,91,125],"by":[16],"inferring":[17],"production":[18,84,151],"attributes":[19],"from":[20],"reference":[22,94],"song.":[23],"However,":[24],"existing":[25],"systems":[26],"mixing":[28,76,107],"are":[31],"limited":[32],"in":[33,50,56],"that":[34],"they":[35],"often":[36],"operate":[37],"only":[38],"on":[39],"fixed":[41],"number":[42,122],"tracks,":[44],"introduce":[45,69],"artifacts,":[46],"and":[47,62,81,92,112,140,154,165],"produce":[48],"mixes":[49,111],"an":[51,82,120],"end-to-end":[52],"fashion,":[53],"without":[54,126],"grounding":[55],"traditional":[57],"audio":[58,83,102,150],"effects,":[59],"prohibiting":[60],"interpretability":[61],"controllability.":[63],"To":[64],"overcome":[65],"these":[66],"challenges,":[67],"we":[68],"Diff-MST,":[70],"framework":[72],"comprising":[73],"differentiable":[75,106],"console,":[77,108],"transformer":[79],"controller,":[80],"loss":[86],"function.":[87],"By":[88],"inputting":[89],"raw":[90],"song,":[95],"our":[96,117,134,145],"model":[97],"estimates":[98],"control":[99],"parameters":[100],"effects":[103],"within":[104],"producing":[109],"high-quality":[110],"enabling":[113,129],"post-hoc":[114],"adjustments.":[115],"Moreover,":[116],"architecture":[118],"supports":[119],"arbitrary":[121],"input":[124],"source":[127],"labelling,":[128],"real-world":[130],"applications.":[131],"We":[132,162],"evaluate":[133],"model's":[135],"performance":[136],"against":[137],"robust":[138],"baselines":[139],"showcase":[141],"effectiveness":[143],"approach,":[146],"architectural":[147],"design,":[148],"tailored":[149],"loss,":[153],"innovative":[155],"training":[156],"methodology":[157],"task.":[161],"provide":[163],"code":[164],"listening":[166],"examples":[167],"online.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
