{"id":"https://openalex.org/W6892524507","doi":"https://doi.org/10.5281/zenodo.10265417","title":"Music Source Separation With MLP Mixing of Time, Frequency, and Channel","display_name":"Music Source Separation With MLP Mixing of Time, Frequency, and Channel","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892524507","doi":"https://doi.org/10.5281/zenodo.10265417"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265417","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265417","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tomoyasu Nakano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Masataka Goto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10175","display_name":"Advanced DC-DC Converters","score":0.5985999703407288,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10175","display_name":"Advanced DC-DC Converters","score":0.5985999703407288,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10361","display_name":"Silicon Carbide Semiconductor Technologies","score":0.2304999977350235,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11248","display_name":"Advanced Power Amplifier Design","score":0.01769999973475933,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8539999723434448},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6538000106811523},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5217000246047974},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.48890000581741333},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45910000801086426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4196999967098236},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4097999930381775},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.3926999866962433}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8539999723434448},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5774000287055969},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5217000246047974},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.48890000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.43140000104904175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4097999930381775},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3321000039577484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C2779127903","wikidata":"https://www.wikidata.org/wiki/Q6510194","display_name":"Learning rule","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265417","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265417","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265417","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265417","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":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4747479259967804,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1,120],"proposes":[2],"a":[3,104,115,123,129],"new":[4],"music":[5],"source":[6],"separation":[7],"(MSS)":[8],"model":[9,124,171],"based":[10,28],"on":[11,29],"an":[12,110],"architecture":[13,75,111,134],"with":[14,31,88,157,178],"MLP-Mixer":[15,133],"that":[16,37,135,168],"leverages":[17],"multilayer":[18],"perceptrons":[19],"(MLPs).":[20],"Most":[21],"of":[22,50,131],"the":[23,48,51,63,73,93,98,132,162,169],"recent":[24],"MSS":[25,113,180],"techniques":[26],"are":[27],"architectures":[30,87],"CNNs,":[32],"RNNs,":[33],"and":[34,90,140,144],"attention-based":[35],"transformers":[36,91],"take":[38],"waveforms":[39],"or":[40,43,84],"complex":[41,149],"spectrograms":[42,150],"both":[44],"as":[45,81,83,114,151],"inputs.":[46],"For":[47],"growth":[49],"research":[52],"field,":[53],"we":[54,102,121],"believe":[55],"it":[56],"is":[57,128],"important":[58],"to":[59,79,106,112],"study":[60],"not":[61],"only":[62],"current":[64],"established":[65],"methodologies":[66],"but":[67],"also":[68],"diverse":[69],"perspectives.":[70],"Therefore,":[71],"since":[72],"MLP-Mixer-based":[74],"has":[76],"been":[77],"reported":[78],"perform":[80],"well":[82],"better":[85],"than":[86],"CNNs":[89],"in":[92],"computer":[94],"vision":[95],"field":[96],"despite":[97],"MLP's":[99],"simple":[100],"computation,":[101],"report":[103],"way":[105],"effectively":[107],"apply":[108],"such":[109],"reusable":[116],"insight.":[117],"In":[118],"this":[119],"propose":[122],"called":[125],"TFC-MLP,":[126],"which":[127],"variant":[130],"preserves":[136],"time-frequency":[137],"positional":[138],"relationships":[139],"mixes":[141],"time,":[142],"frequency,":[143],"channel":[145],"dimensions":[146],"separately,":[147],"using":[148,161],"input.":[152],"The":[153],"TFC-MLP":[154],"was":[155],"evaluated":[156],"source-to-distortion":[158],"ratio":[159],"(SDR)":[160],"MUSDB18-HQ":[163],"dataset.":[164],"Experimental":[165],"results":[166],"showed":[167],"proposed":[170],"can":[172],"achieve":[173],"competitive":[174],"SDRs":[175],"when":[176],"compared":[177],"state-of-the-art":[179],"models.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}