{"id":"https://openalex.org/W4415709368","doi":"https://doi.org/10.1109/icme59968.2025.11208966","title":"Towards Practical Real-Time Low-Latency Music Source Separation","display_name":"Towards Practical Real-Time Low-Latency Music Source Separation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709368","doi":"https://doi.org/10.1109/icme59968.2025.11208966"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102696462","display_name":"Junyu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Wu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052226742","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0002-9297-7729"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114012695","display_name":"Tianrui Pan","orcid":"https://orcid.org/0009-0002-8195-2005"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Pan","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012761","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0002-6086-3559"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39022092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5378999710083008,"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":0.5378999710083008,"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":0.420199990272522,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/limiting","display_name":"Limiting","score":0.666100025177002},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6414999961853027},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5385000109672546},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.445499986410141},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4194999933242798},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869000196456909},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120999813079834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49309998750686646},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29420000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2123493075","https://openalex.org/W2155364762","https://openalex.org/W2233116163","https://openalex.org/W2563637302","https://openalex.org/W2604319603","https://openalex.org/W2669032454","https://openalex.org/W2796571515","https://openalex.org/W2903502793","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963163009","https://openalex.org/W2963992487","https://openalex.org/W2982083293","https://openalex.org/W2997938083","https://openalex.org/W3015199127","https://openalex.org/W3028029645","https://openalex.org/W3113032861","https://openalex.org/W3160050861","https://openalex.org/W3199957557","https://openalex.org/W4224938485","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W4392903354","https://openalex.org/W4392903379","https://openalex.org/W4392903460","https://openalex.org/W4405633843"],"related_works":[],"abstract_inverted_index":{"In":[0,62,87],"recent":[1],"years,":[2],"significant":[3],"progress":[4],"has":[5,19,48],"been":[6,20],"made":[7],"in":[8,59,110],"the":[9,51,82,102,116],"field":[10],"of":[11,53,104,118],"deep":[12],"learning":[13],"for":[14,31],"music":[15,26],"demixing.":[16],"However,":[17],"there":[18],"limited":[21],"attention":[22],"on":[23,81,96],"real-time,":[24],"low-latency":[25,70],"demixing,":[27],"which":[28,78],"holds":[29],"potential":[30],"various":[32],"applications,":[33],"such":[34],"as":[35],"hearing":[36],"aids,":[37],"audio":[38],"stream":[39],"remixing,":[40],"and":[41,133],"live":[42],"performances.":[43],"Additionally,":[44],"a":[45,67,91],"notable":[46],"tendency":[47],"emerged":[49],"towards":[50],"development":[52],"larger":[54],"models,":[55],"limiting":[56],"their":[57],"applicability":[58],"certain":[60],"scenarios.":[61],"this":[63],"paper,":[64],"we":[65,89,114],"introduce":[66],"lightweight":[68],"real-time":[69,111],"model":[71],"called":[72],"Real-Time":[73],"Single-Path":[74],"TFC-TDF":[75,84],"UNET":[76,85],"(RT-STT),":[77],"is":[79],"based":[80,95],"Dual-Path":[83],"(DTTNet).":[86],"RT-STT,":[88],"propose":[90],"feature":[92],"fusion":[93],"technique":[94],"channel":[97],"expansion.":[98],"We":[99],"also":[100],"demonstrate":[101],"superiority":[103],"single-path":[105],"modeling":[106,109],"over":[107],"dual-path":[108],"models.":[112,140],"Moreover,":[113],"investigate":[115],"method":[117],"quantization":[119],"to":[120,138],"further":[121],"reduce":[122],"inference":[123,135],"time.":[124],"RT-STT":[125],"exhibits":[126],"superior":[127],"performance":[128],"with":[129],"significantly":[130],"fewer":[131],"parameters":[132],"shorter":[134],"times":[136],"compared":[137],"state-of-the-art":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}