{"id":"https://openalex.org/W4400800452","doi":"https://doi.org/10.1186/s13636-024-00354-6","title":"The whole is greater than the sum of its parts: improving music source separation by bridging networks","display_name":"The whole is greater than the sum of its parts: improving music source separation by bridging networks","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400800452","doi":"https://doi.org/10.1186/s13636-024-00354-6"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00354-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00354-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00354-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00354-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010892279","display_name":"Ryosuke Sawata","orcid":"https://orcid.org/0000-0003-3230-4335"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryosuke Sawata","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3230-4335","affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010554448","display_name":"Stefan Uhlich","orcid":"https://orcid.org/0000-0003-3158-4945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Uhlich","raw_affiliation_strings":["Sony Europe B.V., Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Europe B.V., Stuttgart, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010892279"],"corresponding_institution_ids":["https://openalex.org/I4210122684"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.9403,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73139794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/bridging","display_name":"Bridging (networking)","score":0.8343507051467896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8206303715705872},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6711165904998779},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6390581130981445},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5100701451301575},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4921852648258209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39766472578048706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35027164220809937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3399662971496582}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8343507051467896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206303715705872},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6711165904998779},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6390581130981445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5100701451301575},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4921852648258209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39766472578048706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35027164220809937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3399662971496582},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00354-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00354-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00354-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4cb69dcbfae44923b88de1070dc8e3a1","is_oa":true,"landing_page_url":"https://doaj.org/article/4cb69dcbfae44923b88de1070dc8e3a1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-19 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00354-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00354-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00354-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400800452.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W85058473","https://openalex.org/W1498436455","https://openalex.org/W1510355813","https://openalex.org/W1555814299","https://openalex.org/W1594771616","https://openalex.org/W1842657353","https://openalex.org/W1901129140","https://openalex.org/W2062710265","https://openalex.org/W2101926813","https://openalex.org/W2113990625","https://openalex.org/W2143027228","https://openalex.org/W2179490238","https://openalex.org/W2285559681","https://openalex.org/W2401104373","https://openalex.org/W2478884216","https://openalex.org/W2563534197","https://openalex.org/W2669032454","https://openalex.org/W2752782242","https://openalex.org/W2760103357","https://openalex.org/W2889134433","https://openalex.org/W2903502793","https://openalex.org/W2913340405","https://openalex.org/W2952218014","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964070952","https://openalex.org/W2972411915","https://openalex.org/W2972653970","https://openalex.org/W2998161426","https://openalex.org/W3015201698","https://openalex.org/W3015372568","https://openalex.org/W3096159803","https://openalex.org/W3099330747","https://openalex.org/W3113792747","https://openalex.org/W3131332223","https://openalex.org/W3160050861","https://openalex.org/W3162801840","https://openalex.org/W3174280965","https://openalex.org/W4372260250","https://openalex.org/W4372265740","https://openalex.org/W4375928773","https://openalex.org/W6600538138","https://openalex.org/W6603578652"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"presents":[3],"the":[4,10,42,53,57,67,71,75,96,99,141,149,155,161,198],"crossing":[5],"scheme":[6],"(X-scheme)":[7],"for":[8,83],"improving":[9],"performance":[11],"of":[12,29,56,62,74,98,151,163,200],"deep":[13],"neural":[14],"network":[15,72,176],"(DNN)-based":[16],"music":[17],"source":[18],"separation":[19,123,175],"(MSS)":[20],"with":[21,179,191,210],"almost":[22],"no":[23],"increasing":[24],"calculation":[25],"cost.":[26],"It":[27],"consists":[28],"three":[30],"components:":[31],"(i)":[32],"multi-domain":[33],"loss":[34,49,129],"(MDL),":[35],"(ii)":[36],"bridging":[37,81],"operation":[38,145],",":[39],"which":[40,218],"couples":[41],"individual":[43],"instrument":[44,86],"networks,":[45],"and":[46,59,114,137,171,186,225],"(iii)":[47],"combination":[48],"(CL).":[50],"MDL":[51,91,113],"enables":[52],"taking":[54],"advantage":[55],"frequency-":[58],"time-domain":[60,173],"representations":[61],"audio":[63,174],"signals.":[64],"We":[65,195],"modify":[66],"target":[68],"network,":[69],"i.e.,":[70],"architecture":[73],"original":[76,193],"DNN-based":[77,122],"MSS,":[78],"by":[79,188],"adding":[80],"paths":[82],"each":[84,105],"output":[85,100],"to":[87,95,120,212],"share":[88],"their":[89,192],"information.":[90],"is":[92,230],"then":[93],"applied":[94,119],"combinations":[97],"sources":[101],"as":[102,104,125],"well":[103],"independent":[106],"source;":[107],"hence,":[108],"we":[109],"called":[110,183],"it":[111],"CL.":[112],"CL":[115],"can":[116],"easily":[117],"be":[118],"many":[121],"methods":[124],"they":[126],"are":[127,132],"merely":[128],"functions":[130],"that":[131,160],"only":[133],"used":[134,226],"during":[135],"training":[136],"do":[138],"not":[139,147],"affect":[140],"inference":[142],"step.":[143],"Bridging":[144],"does":[146],"increase":[148],"number":[150],"learnable":[152],"parameters":[153],"in":[154,202,227],"network.":[156],"Experimental":[157],"results":[158],"showed":[159],"validity":[162],"Open-Unmix":[164],"(UMX),":[165],"densely":[166],"connected":[167],"dilated":[168],"DenseNet":[169],"(D3Net)":[170],"convolutional":[172],"(Conv-TasNet)":[177],"extended":[178],"our":[180,228],"X-scheme,":[181],"respectively":[182],"X-UMX,":[184],"X-D3Net":[185],"X-Conv-TasNet,":[187],"comparing":[189],"them":[190],"versions.":[194],"also":[196],"verified":[197],"effectiveness":[199],"X-scheme":[201],"a":[203],"large-scale":[204,222],"data":[205,213,224],"regime,":[206],"showing":[207],"its":[208],"generality":[209],"respect":[211],"size.":[214],"X-UMX":[215],"Large":[216],"(X-UMXL),":[217],"was":[219],"trained":[220],"on":[221],"internal":[223],"experiments,":[229],"newly":[231],"available":[232],"at":[233],"https://github.com/asteroid-team/asteroid/tree/master/egs/musdb18/X-UMX":[234],".":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-07-19T00:00:00"}