{"id":"https://openalex.org/W7148437033","doi":"https://doi.org/10.1109/asru65441.2025.11434756","title":"A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References <sup>*</sup>","display_name":"A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References <sup>*</sup>","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148437033","doi":"https://doi.org/10.1109/asru65441.2025.11434756"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"display_name":"Simon Dahl Jepsen","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Simon Dahl Jepsen","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab,Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020107710","display_name":"Maria Hornstrup Christensen","orcid":"https://orcid.org/0000-0002-4985-4491"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab,Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132816576","display_name":"Jesper Rindom Jensen","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Rindom Jensen","raw_affiliation_strings":["Aalborg University,Audio Analysis Lab,Denmark"],"affiliations":[{"raw_affiliation_string":"Aalborg University,Audio Analysis Lab,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74179845,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7461000084877014,"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":0.7461000084877014,"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":0.07010000199079514,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.027699999511241913,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/separation-method","display_name":"Separation method","score":0.4553999900817871},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4284000098705292},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3864000141620636},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.37560001015663147},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C3018256011","wikidata":"https://www.wikidata.org/wiki/Q898987","display_name":"Separation method","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44290000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44040000438690186},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.41499999165534973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4034999907016754},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3864000141620636},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C135593079","wikidata":"https://www.wikidata.org/wiki/Q1750766","display_name":"Scale invariance","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C87698059","wikidata":"https://www.wikidata.org/wiki/Q1808960","display_name":"LTI system theory","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2606000006198883},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6413122415542603}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1728888090","https://openalex.org/W1952003395","https://openalex.org/W1964538581","https://openalex.org/W2035576074","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2123879651","https://openalex.org/W2135823751","https://openalex.org/W2143169494","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2594607416","https://openalex.org/W2696967604","https://openalex.org/W2735663686","https://openalex.org/W2889540509","https://openalex.org/W2890075319","https://openalex.org/W2943934118","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W2996969697","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015700067","https://openalex.org/W3015794161","https://openalex.org/W3042857426","https://openalex.org/W3049430014","https://openalex.org/W3096893582","https://openalex.org/W3161480375","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3196475561","https://openalex.org/W3197912330","https://openalex.org/W4200598930","https://openalex.org/W4224936432","https://openalex.org/W4296068774","https://openalex.org/W4319862697","https://openalex.org/W4372271367","https://openalex.org/W4375868852","https://openalex.org/W4375869348","https://openalex.org/W4387938956","https://openalex.org/W4392903841","https://openalex.org/W4392904504","https://openalex.org/W4400877621","https://openalex.org/W4402112435","https://openalex.org/W4402112444","https://openalex.org/W4403126475","https://openalex.org/W4403126636","https://openalex.org/W4408355408"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"the":[3,7,23,30,33,41,50,59,74,97,132,139,142],"implications":[4],"of":[5,40],"using":[6],"Scale-Invariant":[8],"Signal-to-Distortion":[9],"Ratio":[10],"(SI-SDR)":[11],"as":[12,28],"both":[13],"evaluation":[14],"and":[15,72,126,134],"training":[16,24],"objective":[17],"in":[18,58,105],"supervised":[19],"speech":[20,107],"separation,":[21],"when":[22],"references":[25,45,71,112],"contain":[26],"noise,":[27],"is":[29,67,122],"case":[31],"with":[32,43,76,96],"de":[34],"facto":[35],"benchmark":[36],"WSJ0-2Mix.":[37],"A":[38],"derivation":[39],"SI-SDR":[42,125],"noisy":[44,85],"reveals":[46],"that":[47,82,110],"noise":[48,57,104],"limits":[49],"achievable":[51],"SI-SDR,":[52],"or":[53],"leads":[54],"to":[55,69,79],"undesired":[56],"separated":[60,106],"outputs.":[61],"To":[62],"address":[63],"this,":[64],"a":[65],"method":[66],"proposed":[68],"enhance":[70],"augment":[73],"mixtures":[75],"WHAM!,":[77],"aiming":[78],"train":[80],"models":[81,88,130],"avoid":[83],"learning":[84],"references.":[86],"Two":[87],"trained":[89],"on":[90,131],"these":[91],"enhanced":[92],"datasets":[93],"are":[94],"evaluated":[95],"non-intrusive":[98],"NISQA.v2":[99],"metric.":[100],"Results":[101],"show":[102],"reduced":[103],"but":[108],"suggest":[109],"processing":[111],"may":[113],"introduce":[114],"artefacts,":[115],"limiting":[116],"overall":[117],"quality":[118],"gains.":[119],"Negative":[120],"correlation":[121],"found":[123],"between":[124],"perceived":[127],"noisiness":[128],"across":[129],"WSJ0-2Mix":[133],"Libri2Mix":[135],"test":[136],"sets,":[137],"underlining":[138],"conclusion":[140],"from":[141],"derivation.":[143]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}