{"id":"https://openalex.org/W6893344509","doi":"https://doi.org/10.5281/zenodo.15911723","title":"Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation Models","display_name":"Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation Models","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W6893344509","doi":"https://doi.org/10.5281/zenodo.15911723"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15911723","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15911723","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15911723","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bereuter, Paul Armin","orcid":"https://orcid.org/0009-0003-9530-337X"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Bereuter, Paul Armin","raw_affiliation_strings":["University of Music and Performing Arts Graz"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts Graz","institution_ids":["https://openalex.org/I317320687"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stahl, Benjamin","orcid":"https://orcid.org/0000-0001-6446-0039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stahl, Benjamin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Plumbley, Mark","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Plumbley, Mark","raw_affiliation_strings":["University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sontacchi, Alois","orcid":"https://orcid.org/0009-0008-9205-209X"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sontacchi, Alois","raw_affiliation_strings":["University of Music and Performing Arts Graz"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts Graz","institution_ids":["https://openalex.org/I317320687"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I317320687"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7419000267982483},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.580299973487854},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5465999841690063},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5016000270843506},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4465999901294708},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.39640000462532043}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282000184059143},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.580299973487854},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4465000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C90697598","wikidata":"https://www.wikidata.org/wiki/Q3657183","display_name":"Objective test","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15911723","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15911723","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.15911723","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15911723","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"},"sustainable_development_goals":[{"score":0.7615893483161926,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"upload":[1],"accompanies":[2],"the":[3,20,26,32,38,49,74,77,80,104],"WASPAA":[4],"2025":[5],"paper,":[6],"'Towards":[7],"Reliable":[8],"Objective":[9],"Evaluation":[10],"Metrics":[11],"for":[12,62,83],"Generative":[13],"Singing":[14],"Voice":[15],"Separation":[16],"Models'.":[17],"It":[18],"contains":[19],"evaluation":[21,27,81],"audio":[22],"used":[23,36,54],"to":[24,55,98],"compute":[25],"metrics,":[28],"as":[29,31],"well":[30],"loudness-normalised":[33],"test":[34],"stimuli":[35],"in":[37,103],"DCR":[39],"test.":[40],"Also":[41],"included":[42,102],"is":[43],"a":[44],"CSV":[45],"file":[46,92],"containing":[47],"all":[48],"metrics":[50,82,100],"and":[51,66,79],"DMOS":[52,78],"scores":[53],"calculate":[56],"Spearman's":[57],"rank-based":[58],"correlation":[59],"coefficients":[60],"(SRCCs)":[61],"evaluating":[63],"both":[64,84],"discriminative":[65],"generative":[67],"models.A":[68],"demonstration":[69],"Python":[70],"script":[71],"outlines":[72],"how":[73,97],"SRCCs":[75],"between":[76],"types":[85],"of":[86],"model":[87],"are":[88],"calculated.":[89],"The":[90],"Readme.md":[91],"provides":[93],"step-by-step":[94],"instructions":[95],"on":[96],"benchmark":[99],"not":[101],"analysis.":[105]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}