{"id":"https://openalex.org/W4416251705","doi":"https://doi.org/10.1109/waspaa66052.2025.11230966","title":"Beyond Architecture: The Critical Impact of Inference Overlap on Music Source Separation Benchmarks","display_name":"Beyond Architecture: The Critical Impact of Inference Overlap on Music Source Separation Benchmarks","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251705","doi":"https://doi.org/10.1109/waspaa66052.2025.11230966"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5120499614","display_name":"Harnick Khera","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Harnick Khera","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048509747","display_name":"Johan Pauwels","orcid":"https://orcid.org/0000-0002-5805-7144"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Johan Pauwels","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022641011","display_name":"Alan Archer-Boyd","orcid":"https://orcid.org/0000-0001-8828-4295"},"institutions":[{"id":"https://openalex.org/I195557943","display_name":"Lighthouse Guild","ror":"https://ror.org/00tzd7r06","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I195557943"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W. Archer-Boyd","raw_affiliation_strings":["The Lighthouse,BBC Research and Development,London,United Kingdom,W12 7TQ"],"affiliations":[{"raw_affiliation_string":"The Lighthouse,BBC Research and Development,London,United Kingdom,W12 7TQ","institution_ids":["https://openalex.org/I195557943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076173089","display_name":"M. Sandler","orcid":"https://orcid.org/0000-0002-5691-8107"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark B. Sandler","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,United Kingdom,E1 4NS","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120499614"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":1.6611,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88343043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8428999781608582,"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":0.8428999781608582,"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":0.06930000334978104,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.05050000175833702,"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/inference","display_name":"Inference","score":0.82669997215271},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.5478000044822693},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5426999926567078},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.48669999837875366},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4602000117301941},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4399999976158142},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.82669997215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5964999794960022},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431000053882599},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.35429999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3343999981880188},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C188642973","wikidata":"https://www.wikidata.org/wiki/Q2855754","display_name":"Six degrees of separation","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W2115144768","https://openalex.org/W2963838685","https://openalex.org/W2963992487","https://openalex.org/W2972411915","https://openalex.org/W3037149862","https://openalex.org/W3161022068","https://openalex.org/W3199957557","https://openalex.org/W4327814100","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W4392909836"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"how":[3],"inference":[4,76,140],"step":[5],"size":[6],"in":[7],"sliding":[8],"window":[9],"approaches":[10],"affects":[11],"music":[12],"source":[13],"separation":[14,34],"quality.":[15],"Through":[16],"systematic":[17],"analysis":[18,68],"of":[19,113],"seven":[20],"model":[21],"configurations":[22],"across":[23],"five":[24],"architectures,":[25],"we":[26],"demonstrate":[27],"that":[28,118,129],"increased":[29,105],"segment":[30],"overlap":[31,77,86,106,120],"consistently":[32],"improves":[33,49],"quality":[35,91],"by":[36],"up":[37],"to":[38,64,132],"0.37":[39],"dB":[40],"SDR.":[41,114],"We":[42],"identify":[43],"a":[44],"universal":[45],"pattern":[46],"where":[47,61],"performance":[48],"logarithmically":[50],"with":[51,53],"overlap,":[52],"an":[54],"\"elbow":[55],"point\"":[56],"at":[57],"4-8":[58],"overlapping":[59],"segments":[60],"efficiency":[62],"begins":[63],"decrease":[65],"rapidly.":[66],"Our":[67],"reveals":[69],"that:":[70],"(1)":[71],"state-of-the-art":[72],"papers":[73],"inconsistently":[74],"report":[75],"settings,":[78],"making":[79],"fair":[80],"comparisons":[81,127],"difficult;":[82],"(2)":[83],"even":[84],"modest":[85],"settings":[87],"(25%)":[88],"substantially":[89],"improve":[90],"through":[92],"boundary":[93],"artifact":[94],"reduction;":[95],"and":[96,128],"(3)":[97],"higher-performing":[98],"models":[99],"show":[100],"proportionally":[101],"greater":[102],"improvements":[103],"from":[104,138],"when":[107],"accounting":[108],"for":[109,124],"the":[110],"logarithmic":[111],"nature":[112],"These":[115],"findings":[116],"suggest":[117],"standardized":[119],"reporting":[121],"is":[122],"essential":[123],"meaningful":[125],"architectural":[126,133],"differences":[130],"attributed":[131],"innovations":[134],"may":[135],"partly":[136],"stem":[137],"undisclosed":[139],"settings.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}