{"id":"https://openalex.org/W7108626009","doi":"https://doi.org/10.5281/zenodo.17811344","title":"Tuning Matters: Analyzing Musical Tuning Bias in Neural Vocoders","display_name":"Tuning Matters: Analyzing Musical Tuning Bias in Neural Vocoders","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108626009","doi":"https://doi.org/10.5281/zenodo.17811344"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811344","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hans-Ulrich Berendes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans-Ulrich Berendes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ben Maman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Maman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Meinard M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52165729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.2757999897003174,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.2757999897003174,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.17080000042915344,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.13459999859333038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5333999991416931},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.38199999928474426},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.34700000286102295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33480000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769599974155426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6194000244140625},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5333999991416931},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.27250000834465027}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811344","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811344","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811344","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":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.43972277641296387,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vocoders,":[0],"which":[1,33],"reconstruct":[2],"time-domain":[3],"waveforms":[4],"from":[5],"spectral":[6],"representations":[7],"such":[8],"as":[9],"mel-spectrograms,":[10],"are":[11],"essential":[12],"in":[13,54,119,126,140],"modern":[14,84],"music":[15,141],"and":[16,48,104,121,143],"speech":[17],"synthesis.":[18],"Traditional":[19],"signal-processing":[20],"techniques":[21],"like":[22],"the":[23,71,83,134],"Griffin-Lim":[24],"algorithm":[25],"have":[26],"largely":[27],"been":[28],"replaced":[29],"by":[30],"neural":[31,67,97],"vocoders,":[32],"leverage":[34],"generative":[35],"models":[36,44],"to":[37,82],"achieve":[38],"superior":[39],"audio":[40],"quality.":[41],"However,":[42],"these":[43],"can":[45],"introduce":[46],"artifacts":[47],"biases,":[49,116],"potentially":[50],"affecting":[51,122],"their":[52],"output":[53],"unforeseen":[55],"ways.":[56],"In":[57],"this":[58],"study,":[59],"we":[60,93],"examine":[61],"how":[62],"different":[63,112],"musical":[64],"tunings":[65],"affect":[66],"mel-to-audio":[68],"vocoders":[69,98,113],"within":[70],"context":[72],"of":[73,128],"Western":[74],"music,":[75],"where":[76],"performances":[77],"do":[78],"not":[79],"necessarily":[80],"adhere":[81],"440":[85],"Hz":[86],"standard":[87],"tuning.":[88,130],"As":[89],"a":[90],"key":[91],"contribution,":[92],"evaluate":[94],"several":[95],"recent":[96],"on":[99],"datasets":[100],"containing":[101],"piano,":[102],"violin,":[103],"singing":[105],"voice":[106],"recordings.":[107],"Our":[108,131],"results":[109],"reveal":[110],"that":[111],"exhibit":[114],"distinct":[115],"causing":[117],"deviation":[118],"tuning,":[120],"waveform":[123],"reconstruction":[124],"quality":[125],"case":[127],"non-standard":[129],"work":[132],"underscores":[133],"need":[135],"for":[136,146],"improved":[137],"vocoder":[138],"robustness":[139],"synthesis":[142],"provides":[144],"insights":[145],"refining":[147],"future":[148],"models.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}