{"id":"https://openalex.org/W4413118584","doi":"https://doi.org/10.1109/access.2025.3596644","title":"Three Years of VoiceMOS Challenges: Lessons Learned by the UWB-NTIS-TTS Team","display_name":"Three Years of VoiceMOS Challenges: Lessons Learned by the UWB-NTIS-TTS Team","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413118584","doi":"https://doi.org/10.1109/access.2025.3596644"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3596644","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596644","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3596644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050568080","display_name":"Marie Kune\u0161ov\u00e1","orcid":"https://orcid.org/0000-0002-7187-8481"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Marie Kune\u0161ov\u00e1","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7187-8481","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030642609","display_name":"Jind\u0159ich Matou\u0161ek","orcid":"https://orcid.org/0000-0002-7408-7730"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jind\u0159ich Matou\u0161ek","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7408-7730","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085434299","display_name":"Jan Lehe\u010dka","orcid":"https://orcid.org/0000-0002-3889-8069"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Lehe\u010dka","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-3889-8069","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u0160vec","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-8362-5927","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029012602","display_name":"Daniel Tihelka","orcid":"https://orcid.org/0000-0002-3149-2330"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Daniel Tihelka","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-3149-2330","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064576255","display_name":"Zden\u011bk Hanzl\u00ed\u010dek","orcid":"https://orcid.org/0000-0002-4001-9289"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zden\u011bk Hanzl\u00ed\u010dek","raw_affiliation_strings":["Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-4001-9289","affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.5352,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69134228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":null,"first_page":"140152","last_page":"140174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12024","display_name":"Ultra-Wideband Communications Technology","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12024","display_name":"Ultra-Wideband Communications Technology","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11993","display_name":"Atomic and Subatomic Physics Research","score":0.9567000269889832,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11175","display_name":"Gyrotron and Vacuum Electronics Research","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5227006673812866},{"id":"https://openalex.org/keywords/aeronautics","display_name":"Aeronautics","score":0.3341778814792633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2740997076034546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5227006673812866},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.3341778814792633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2740997076034546}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3596644","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596644","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:391a01ed4a114d129f75534cad62cdd0","is_oa":true,"landing_page_url":"https://doaj.org/article/391a01ed4a114d129f75534cad62cdd0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 140152-140174 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3596644","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3596644","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7136309095","display_name":null,"funder_award_id":"GA22-27800S","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W78403783","https://openalex.org/W1552314771","https://openalex.org/W2078597717","https://openalex.org/W2107860279","https://openalex.org/W2113131123","https://openalex.org/W2131490903","https://openalex.org/W2474880636","https://openalex.org/W2511311723","https://openalex.org/W2741434784","https://openalex.org/W2757712123","https://openalex.org/W2890411931","https://openalex.org/W2962780374","https://openalex.org/W2963403924","https://openalex.org/W2970656761","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W3015537910","https://openalex.org/W3047992192","https://openalex.org/W3147454823","https://openalex.org/W3161558238","https://openalex.org/W3163596559","https://openalex.org/W3196225973","https://openalex.org/W3198429080","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3213029956","https://openalex.org/W4225302959","https://openalex.org/W4225956675","https://openalex.org/W4226198268","https://openalex.org/W4296068818","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4297841773","https://openalex.org/W4311167834","https://openalex.org/W4372260498","https://openalex.org/W4385822628","https://openalex.org/W4386058772","https://openalex.org/W4386389284","https://openalex.org/W4390912357","https://openalex.org/W4391021560","https://openalex.org/W4391021724","https://openalex.org/W4402112395","https://openalex.org/W4404160901","https://openalex.org/W4406461503"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Automatic":[0],"prediction":[1,47,176],"of":[2,38,112,135,140,171],"mean-opinion":[3],"scores":[4],"(MOS)":[5],"promises":[6],"a":[7,23],"faster,":[8],"cheaper":[9],"alternative":[10],"to":[11,167],"listening":[12],"tests,":[13],"yet":[14],"robust":[15],"generalization":[16],"across":[17],"speakers,":[18],"languages,":[19],"and":[20,32,53,58,73,76,106,110],"domains":[21],"remains":[22],"significant":[24],"challenge.":[25],"This":[26],"article":[27],"presents":[28],"our":[29],"system":[30],"designs":[31],"experimental":[33],"results":[34],"from":[35],"three":[36],"years":[37],"participation":[39],"in":[40,126],"the":[41,90,108,119,130,138,153,169],"VoiceMOS":[42],"Challenges":[43],"(2022\u20132024),":[44],"covering":[45],"MOS":[46,175],"for":[48],"synthesized":[49],"or":[50],"voice-converted":[51],"speech":[52],"singing":[54],"voice,":[55],"including":[56],"out-of-domain":[57,141],"cross-language":[59],"conditions.":[60],"We":[61,162],"evaluate":[62],"six":[63],"neural":[64],"architectures":[65],"\u2013":[66,75],"wav2vec":[67],"2.0,":[68],"QuartzNet,":[69],"CNN-RNN,":[70],"LDNet,":[71],"RawNet3,":[72],"HiFi-GAN":[74],"their":[77],"ensembles.":[78],"Across":[79],"all":[80],"tasks,":[81],"we":[82],"find":[83],"that":[84,123,146],"1)":[85],"self-supervised":[86],"acoustic":[87],"encoders":[88],"are":[89,104],"most":[91],"consistently":[92],"reliable":[93],"foundation,":[94],"2)":[95],"ensembling":[96],"yields":[97],"rapidly":[98],"diminishing":[99],"returns":[100],"once":[101],"complementary":[102],"representations":[103],"covered,":[105],"3)":[107],"diversity":[109],"balance":[111],"training":[113],"data":[114],"outweigh":[115],"architectural":[116],"complexity.":[117],"Notably,":[118],"indiscriminate":[120],"fusion":[121],"strategy":[122],"performed":[124],"well":[125],"2022":[127],"degrades":[128],"under":[129],"mismatched":[131],"French":[132],"TTS":[133],"conditions":[134],"2023,":[136],"emphasizing":[137],"importance":[139],"validation.":[142],"Further":[143],"experiments":[144],"show":[145],"carefully":[147],"pruned":[148],"ensembles":[149],"can":[150],"modestly":[151],"outperform":[152],"best":[154],"single":[155],"model":[156],"while":[157],"remaining":[158],"within":[159],"real-time":[160],"constraints.":[161],"conclude":[163],"with":[164],"several":[165],"observations":[166],"guide":[168],"development":[170],"computationally":[172],"efficient,":[173],"domain-robust":[174],"systems.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}