{"id":"https://openalex.org/W4392903379","doi":"https://doi.org/10.1109/icassp48485.2024.10446843","title":"Music Source Separation With Band-Split Rope Transformer","display_name":"Music Source Separation With Band-Split Rope Transformer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903379","doi":"https://doi.org/10.1109/icassp48485.2024.10446843"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446843","doi":"https://doi.org/10.1109/icassp48485.2024.10446843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446843","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.02612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070642261","display_name":"Wei-Tsung Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229","observed_orcids":["https://orcid.org/0009-0002-8265-4229"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475","observed_orcids":["https://orcid.org/0000-0003-2864-0475"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Amy Hung","orcid":"https://orcid.org/0000-0002-7242-6903","observed_orcids":["https://orcid.org/0000-0002-7242-6903"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":["https://openalex.org/I4405256866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405256866"],"apc_list":null,"apc_paid":null,"fwci":19.4941,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.99514687,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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":0.9926999807357788,"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/T10860","display_name":"Speech and Audio Processing","score":0.0066999997943639755,"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":9.999999747378752e-05,"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/music-source-separation","display_name":"music source separation","score":1.0},{"id":"https://openalex.org/keywords/rotary-position-embedding","display_name":"rotary position embedding","score":0.7269999980926514},{"id":"https://openalex.org/keywords/hierarchical-transformer","display_name":"hierarchical transformer","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7456504106521606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204028367996216},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.709679365158081},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6696332097053528},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5968726277351379},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.591356635093689},{"id":"https://openalex.org/C162269090","wikidata":"https://www.wikidata.org/wiki/Q1156047","display_name":"Rope","level":2,"score":0.5867043733596802},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.5371853113174438},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5210451483726501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4988999366760254},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4766710102558136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45227888226509094},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4319840669631958},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34029892086982727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3317883610725403},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2443314790725708},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1982244849205017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1769229769706726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446843","doi":"https://doi.org/10.1109/icassp48485.2024.10446843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446843","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.02612","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.02612","pdf_url":"https://arxiv.org/pdf/2309.02612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.02612","doi":"https://doi.org/10.48550/arxiv.2309.02612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.02612","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.02612","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.02612","pdf_url":"https://arxiv.org/pdf/2309.02612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903379.pdf","grobid_xml":"https://content.openalex.org/works/W4392903379.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2053165762","https://openalex.org/W2127851351","https://openalex.org/W2567070169","https://openalex.org/W2587994092","https://openalex.org/W2626778328","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2805288670","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W2916985722","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963992487","https://openalex.org/W2970903692","https://openalex.org/W2990594533","https://openalex.org/W2997938083","https://openalex.org/W3037149862","https://openalex.org/W3199957557","https://openalex.org/W3207444892","https://openalex.org/W3213726885","https://openalex.org/W4224918587","https://openalex.org/W4224944643","https://openalex.org/W4225261970","https://openalex.org/W4286980120","https://openalex.org/W4298310324","https://openalex.org/W4372260250","https://openalex.org/W4372260308","https://openalex.org/W4375928773","https://openalex.org/W4376632818","https://openalex.org/W4388979610","https://openalex.org/W4394661832","https://openalex.org/W4394916053","https://openalex.org/W6766320909","https://openalex.org/W7133227460"],"related_works":["https://openalex.org/W4387355932","https://openalex.org/W4375928773","https://openalex.org/W4413278494","https://openalex.org/W4392903354","https://openalex.org/W6892524507","https://openalex.org/W4315786026","https://openalex.org/W4226221107","https://openalex.org/W2994556641","https://openalex.org/W4393104536","https://openalex.org/W4372260250"],"abstract_inverted_index":{"Music":[0,132],"source":[1],"separation":[2],"(MSS)":[3],"aims":[4],"to":[5,70,87,109],"separate":[6],"a":[7,51,59,67,82,141],"music":[8],"recording":[9],"into":[10,76],"multiple":[11],"musically":[12],"distinct":[13],"stems,":[14],"such":[15,26],"as":[16,27,91,93],"vocals,":[17],"bass,":[18],"drums,":[19],"and":[20,32,79,122],"more.":[21],"Recently,":[22],"deep":[23],"learning":[24],"approaches":[25],"convolutional":[28],"neural":[29,34],"networks":[30,35],"(CNNs)":[31],"recurrent":[33],"(RNNs)":[36],"have":[37],"been":[38],"used,":[39],"but":[40],"the":[41,72,89,103,111,127,131],"improvement":[42],"is":[43],"still":[44],"limited.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,107,148],"propose":[50,108],"novel":[52],"frequency-domain":[53],"approach":[54],"(called":[55],"BS-RoFormer)":[56],"based":[57],"on":[58,66,120,146],"Band-Split":[60],"RoPE":[61],"Transformer":[62],"architecture.":[63],"BS-RoFormer":[64,117,145],"relies":[65],"band-split":[68],"module":[69],"project":[71],"input":[73],"complex":[74],"spectrogram":[75],"subband-level":[77],"representations,":[78],"then":[80],"arranges":[81],"stack":[83],"of":[84,135,144,159],"hierarchical":[85],"Transformers":[86],"model":[88,104],"inner-band":[90],"well":[92],"inter-band":[94],"sequences":[95],"for":[96,105],"multi-band":[97],"mask":[98],"estimation.":[99],"To":[100],"facilitate":[101],"training":[102,154],"MSS,":[106],"use":[110],"Rotary":[112],"Position":[113],"Embedding":[114],"(RoPE).":[115],"The":[116],"system":[118],"trained":[119],"MUSDB18HQ":[121],"500":[123],"extra":[124,153],"songs":[125],"ranked":[126],"first":[128],"place":[129],"in":[130],"Separation":[133],"contest":[134],"Sound":[136],"Demixing":[137],"Challenge":[138],"(SDX\u201923).":[139],"Benchmarking":[140],"smaller":[142],"version":[143],"MUSDB18HQ,":[147],"achieve":[149],"state-of-the-art":[150],"result":[151],"without":[152],"data,":[155],"with":[156],"9.80":[157],"dB":[158],"average":[160],"SDR.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-03-19T00:00:00"}