{"id":"https://openalex.org/W4403183151","doi":"https://doi.org/10.1109/is262782.2024.10704085","title":"Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support","display_name":"Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4403183151","doi":"https://doi.org/10.1109/is262782.2024.10704085"},"language":"en","primary_location":{"id":"doi:10.1109/is262782.2024.10704085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","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/A5076817923","display_name":"Karn N. Watcharasupat","orcid":"https://orcid.org/0000-0002-3878-5048"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karn N. Watcharasupat","raw_affiliation_strings":["Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032","Music Informatics Group, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032","institution_ids":["https://openalex.org/I869089601"]},{"raw_affiliation_string":"Music Informatics Group, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055058138","display_name":"Chih-Wei Wu","orcid":"https://orcid.org/0000-0002-9019-6515"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Wei Wu","raw_affiliation_strings":["Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032"],"affiliations":[{"raw_affiliation_string":"Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016069022","display_name":"Iroro Orife","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iroro Orife","raw_affiliation_strings":["Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032"],"affiliations":[{"raw_affiliation_string":"Audio Algorithms, Netflix, Inc.,Los Gatos,CA,USA,95032","institution_ids":["https://openalex.org/I869089601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076817923"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I869089601"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5773102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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":0.9943000078201294,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9643999934196472,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9412999749183655,"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/computer-science","display_name":"Computer science","score":0.6780363917350769},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6222773194313049},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6183168888092041},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4541463553905487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.29758137464523315},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19515764713287354},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07320842146873474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780363917350769},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6222773194313049},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6183168888092041},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4541463553905487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29758137464523315},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19515764713287354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07320842146873474},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is262782.2024.10704085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2121895216","https://openalex.org/W2132227091","https://openalex.org/W2141808894","https://openalex.org/W2461484745","https://openalex.org/W2569587366","https://openalex.org/W2593116425","https://openalex.org/W2747935894","https://openalex.org/W2750167318","https://openalex.org/W2895654193","https://openalex.org/W2968860202","https://openalex.org/W2998657200","https://openalex.org/W3032479101","https://openalex.org/W3092791109","https://openalex.org/W3133417262","https://openalex.org/W3198533616","https://openalex.org/W3204379680","https://openalex.org/W3205879560","https://openalex.org/W4205689591","https://openalex.org/W4213247118","https://openalex.org/W4280499798","https://openalex.org/W4294406066","https://openalex.org/W4384160435","https://openalex.org/W4384928248","https://openalex.org/W4389331832","https://openalex.org/W4391454536","https://openalex.org/W4394896659","https://openalex.org/W6633191696","https://openalex.org/W6732646663","https://openalex.org/W6757817989","https://openalex.org/W6776605602","https://openalex.org/W6777664437","https://openalex.org/W6777781272","https://openalex.org/W6778625279","https://openalex.org/W6779192484","https://openalex.org/W6798326965","https://openalex.org/W6808838539","https://openalex.org/W6869553485"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"Cinematic":[0],"audio":[1,25],"source":[2,26],"separation":[3],"(CASS),":[4],"as":[5],"a":[6,20],"problem":[7],"of":[8,24,69,91,116],"extracting":[9],"the":[10,40,79,92,113,135,148,161,177],"dialogue,":[11],"music,":[12],"and":[13,42,108,142],"effects":[14],"stems":[15],"from":[16,122,127],"their":[17],"mixture,":[18],"is":[19,47],"relatively":[21],"new":[22],"subtask":[23],"separation.":[27],"To":[28],"date,":[29],"only":[30],"one":[31],"publicly":[32],"available":[33],"dataset":[34],"exists":[35],"for":[36,65],"CASS,":[37,66],"that":[38,152],"is,":[39],"Divide":[41],"Remaster":[43],"(DnR)":[44],"dataset,":[45,94],"which":[46],"currently":[48],"at":[49],"version":[50,89],"2.":[51],"While":[52],"D":[53],"<tex":[54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$n$</tex>":[56],"R":[57],"v2":[58],"has":[59],"been":[60,72],"an":[61],"incredibly":[62],"useful":[63],"resource":[64],"several":[67],"areas":[68],"improvement":[70],"have":[71],"identified,":[73],"particularly":[74],"through":[75],"its":[76],"use":[77],"in":[78,101,164,171],"2023":[80],"Sound":[81],"Demixing":[82],"Challenge.":[83],"In":[84,111],"this":[85],"work,":[86],"we":[87],"develop":[88],"3":[90],"DnR":[93,117],"addressing":[95],"issues":[96],"relating":[97],"to":[98,134,160],"vocal":[99],"content":[100,121],"non-dialogue":[102],"stems,":[103],"loudness":[104],"distributions,":[105],"mastering":[106],"process,":[107],"linguistic":[109],"diversity.":[110],"particular,":[112],"dialogue":[114],"stem":[115],"v3":[118],"includes":[119],"speech":[120],"more":[123],"than":[124,186],"30":[125],"languages":[126,165,172],"multiple":[128],"families":[129],"including":[130],"but":[131],"not":[132],"limited":[133],"Germanic,":[136],"Romance,":[137],"Indo-Aryan,":[138],"Dravidian,":[139],"Malayo-":[140],"Polynesian,":[141],"Bantu":[143],"families.":[144],"Benchmark":[145],"results":[146],"using":[147],"Bandit":[149],"model":[150,162,179],"indicated":[151],"training":[153],"on":[154,182,190],"multilingual":[155,178],"data":[156,168,175],"yields":[157],"significant":[158],"generalizability":[159],"even":[163],"with":[166,173],"low":[167],"availability.":[169],"Even":[170],"high":[174],"availability,":[176],"often":[180],"performs":[181],"par":[183],"or":[184],"better":[185],"dedicated":[187],"models":[188],"trained":[189],"monolingual":[191],"CASS":[192],"datasets.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}