{"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","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446843","pdf_url":null,"source":null,"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"},"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/A5070642261","display_name":"Wei-Tsung Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Wei-Tsung Lu","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I43424612","display_name":"Sadat Academy for Management Sciences","ror":"https://ror.org/04scnnc07","country_code":"EG","type":"education","lineage":["https://openalex.org/I43424612"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["SAMI,ByteDance","ByteDance, SAMI"],"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance","institution_ids":["https://openalex.org/I43424612"]},{"raw_affiliation_string":"ByteDance, SAMI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070642261"],"corresponding_institution_ids":["https://openalex.org/I43424612"],"apc_list":null,"apc_paid":null,"fwci":10.181,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98919263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"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/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":0.9991000294685364,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/transformer","display_name":"Transformer","score":0.7456504106521606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204028367996216},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.709679365158081},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6696332097053528},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5968726277351379},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.591356635093689},{"id":"https://openalex.org/keywords/rope","display_name":"Rope","score":0.5867043733596802},{"id":"https://openalex.org/keywords/bass","display_name":"Bass (fish)","score":0.5371853113174438},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5210451483726501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4988999366760254},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4766710102558136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45227888226509094},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4319840669631958},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34029892086982727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3317883610725403},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2443314790725708},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1982244849205017},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1769229769706726}],"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446843","pdf_url":null,"source":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2053165762","https://openalex.org/W2127851351","https://openalex.org/W2567070169","https://openalex.org/W2587994092","https://openalex.org/W2669032454","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W2916985722","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963452667","https://openalex.org/W2963992487","https://openalex.org/W2981040094","https://openalex.org/W2990594533","https://openalex.org/W2997938083","https://openalex.org/W3037149862","https://openalex.org/W3099330747","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/W4226300471","https://openalex.org/W4281758439","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/W4385245566","https://openalex.org/W4388979610","https://openalex.org/W4394661832","https://openalex.org/W4394916053","https://openalex.org/W6731370813","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6766320909","https://openalex.org/W6767440493","https://openalex.org/W6799044462","https://openalex.org/W6801426729","https://openalex.org/W6803003856","https://openalex.org/W6838322825","https://openalex.org/W6853055297"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"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":4},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}