{"id":"https://openalex.org/W4401161619","doi":"https://doi.org/10.1587/transinf.2023edp7044","title":"MDX-Mixer: Music Demixing by Leveraging Source Signals Separated by Existing Demixing Models","display_name":"MDX-Mixer: Music Demixing by Leveraging Source Signals Separated by Existing Demixing Models","publication_year":2024,"publication_date":"2024-07-31","ids":{"openalex":"https://openalex.org/W4401161619","doi":"https://doi.org/10.1587/transinf.2023edp7044"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2023edp7044","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7044","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2023EDP7044/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2023EDP7044/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu NAKANO","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka GOTO","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST)","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.120031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E107.D","issue":"8","first_page":"1079","last_page":"1088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762741446495056},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.573479413986206},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.46674400568008423},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4482033848762512},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4477722644805908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4396061599254608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956510126590729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3502386212348938},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3301636278629303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1511114537715912},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12026464939117432},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1014404296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762741446495056},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.573479413986206},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.46674400568008423},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4482033848762512},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4477722644805908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4396061599254608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956510126590729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3502386212348938},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3301636278629303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1511114537715912},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12026464939117432},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1014404296875},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2023edp7044","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7044","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2023EDP7044/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2023edp7044","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7044","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2023EDP7044/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6748461295","display_name":"Research on Estimation, Utilization, and Control of Preferences for Music Content through the Combination of Informatics and Neuroscience","funder_award_id":"21H04917","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401161619.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W216468625","https://openalex.org/W1522301498","https://openalex.org/W1580780811","https://openalex.org/W2090681206","https://openalex.org/W2101593488","https://openalex.org/W2117438264","https://openalex.org/W2154918349","https://openalex.org/W2286859569","https://openalex.org/W2304609584","https://openalex.org/W2403680808","https://openalex.org/W2508884455","https://openalex.org/W2533278577","https://openalex.org/W2563637302","https://openalex.org/W2669032454","https://openalex.org/W2771189179","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2805288670","https://openalex.org/W2938709889","https://openalex.org/W2952218014","https://openalex.org/W2963751183","https://openalex.org/W2964070952","https://openalex.org/W2972411915","https://openalex.org/W2972964474","https://openalex.org/W2985214749","https://openalex.org/W2986673441","https://openalex.org/W2990594533","https://openalex.org/W2997938083","https://openalex.org/W3001377302","https://openalex.org/W3009168039","https://openalex.org/W3015724290","https://openalex.org/W3015753416","https://openalex.org/W3037149862","https://openalex.org/W3046871516","https://openalex.org/W3081279708","https://openalex.org/W3090496396","https://openalex.org/W3092379909","https://openalex.org/W3099330747","https://openalex.org/W3157506437","https://openalex.org/W3160050861","https://openalex.org/W3160733670","https://openalex.org/W3162801840","https://openalex.org/W3174257816","https://openalex.org/W3183984232","https://openalex.org/W3199384252","https://openalex.org/W3199957557","https://openalex.org/W3212754542","https://openalex.org/W3213726885","https://openalex.org/W3216004336","https://openalex.org/W4225300878","https://openalex.org/W4225300994","https://openalex.org/W4226219311","https://openalex.org/W4285108271","https://openalex.org/W4285222490"],"related_works":["https://openalex.org/W2373038869","https://openalex.org/W2375908649","https://openalex.org/W2614837930","https://openalex.org/W165228748","https://openalex.org/W4239339237","https://openalex.org/W1968967501","https://openalex.org/W2368589579","https://openalex.org/W4387838477","https://openalex.org/W2348671594","https://openalex.org/W2374505530"],"abstract_inverted_index":{"This":[0],"paper":[1,159],"presents":[2],"MDX-Mixer,":[3],"which":[4,81],"improves":[5],"music":[6,131,144],"demixing":[7],"(MDX)":[8],"performance":[9],"by":[10,15,29,54,141,151,179,228],"leveraging":[11],"source":[12,88,127],"signals":[13,52,83,128,146,150,226],"separated":[14,53,82,126,149,225],"multiple":[16],"existing":[17],"MDX":[18,21,56,231],"models.":[19,232],"Deep-learning-based":[20],"models":[22,57],"have":[23,77],"improved":[24],"their":[25,148],"separation":[26,67,73],"performances":[27,200],"year":[28,30],"for":[31,113],"four":[32],"kinds":[33],"of":[34,63,84,124],"sound":[35,87],"sources:":[36],"\u201cvocals,\u201d":[37],"\u201cdrums,\u201d":[38],"\u201cbass,\u201d":[39],"and":[40,74,118,129,147,173],"\u201cother\u201d.":[41],"Our":[42],"research":[43],"question":[44],"is":[45,107,196],"whether":[46],"mixing":[47,99,121],"(i.e.,":[48],"weighted":[49],"sum)":[50],"the":[51,61,85,125,130,143,181,186,205,210,218,224],"state-of-the-art":[55,230],"can":[58],"obtain":[59],"either":[60],"best":[62],"everything":[64],"or":[65,96],"higher":[66,221],"performance.":[68],"Previously,":[69],"in":[70,80,109,185],"singing":[71],"voice":[72],"MDX,":[75],"there":[76],"been":[78],"studies":[79],"same":[86],"are":[89,139],"mixed":[90],"with":[91],"each":[92,191],"other":[93],"using":[94,122,170,209],"time-invariant":[95,168],"time-varying":[97,120,137,177],"positive":[98],"weights.":[100],"In":[101,157],"contrast":[102],"to":[103,190],"those,":[104],"this":[105,158],"study":[106],"novel":[108],"that":[110,166,175,217],"it":[111],"allows":[112],"negative":[114],"weights":[115,138,169,178],"as":[116],"well":[117],"performs":[119],"all":[123],"acoustic":[132,145],"signal":[133],"before":[134],"separation.":[135],"The":[136,193,214],"estimated":[140],"modeling":[142],"dividing":[152],"them":[153],"into":[154],"short":[155],"segments.":[156],"we":[160],"propose":[161],"two":[162],"new":[163],"systems:":[164],"one":[165,174],"estimates":[167,176],"1\u00d71":[171],"convolution,":[172],"applying":[180],"MLP-Mixer":[182],"layer":[183],"proposed":[184],"computer":[187],"vision":[188],"field":[189],"segment.":[192],"latter":[194],"model":[195],"called":[197],"MDX-Mixer.":[198],"Their":[199],"were":[201],"evaluated":[202],"based":[203],"on":[204],"source-to-distortion":[206],"ratio":[207],"(SDR)":[208],"well-known":[211],"MUSDB18-HQ":[212],"dataset.":[213],"results":[215],"show":[216],"MDX-Mixer":[219],"achieved":[220],"SDR":[222],"than":[223],"given":[227],"three":[229]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}