{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:46:44Z","timestamp":1776883604102,"version":"3.51.2"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001824","name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","doi-asserted-by":"publisher","award":["GA22-27800S"],"award-info":[{"award-number":["GA22-27800S"]}],"id":[{"id":"10.13039\/501100001824","id-type":"DOI","asserted-by":"publisher"}]},{"name":"e-INFRA CZ","award":["90254"],"award-info":[{"award-number":["90254"]}]},{"name":"Ministry of Education, Youth and Sports of the Czech Republic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3596644","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:45:34Z","timestamp":1754588734000},"page":"140152-140174","source":"Crossref","is-referenced-by-count":2,"title":["Three Years of VoiceMOS Challenges: Lessons Learned by the UWB-NTIS-TTS Team"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7187-8481","authenticated-orcid":false,"given":"Marie","family":"Kune\u0161ov\u00e1","sequence":"first","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7408-7730","authenticated-orcid":false,"given":"Jind\u0159ich","family":"Matou\u0161ek","sequence":"additional","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-8069","authenticated-orcid":false,"given":"Jan","family":"Lehe\u010dka","sequence":"additional","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8362-5927","authenticated-orcid":false,"given":"Jan","family":"\u0160vec","sequence":"additional","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3149-2330","authenticated-orcid":false,"given":"Daniel","family":"Tihelka","sequence":"additional","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4001-9289","authenticated-orcid":false,"given":"Zden\u011bk","family":"Hanzl\u00ed\u010dek","sequence":"additional","affiliation":[{"name":"Department of Cybernetics, Faculty of Applied Sciences, NTIS Research Center, University of West Bohemia in Pilsen, Pilsen, Czechia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-689"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s41233-016-0002-1"},{"key":"ref7","volume-title":"Mean Opinion Score (MOS) Terminology","year":"2003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-799"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-400"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref19","volume-title":"Methods for Subjective Determination of Transmission Quality","year":"1996"},{"key":"ref20","volume-title":"Subjective Test Methodology for Evaluating Speech Communication Systems That Include Noise Suppression Algorithm","year":"2003"},{"key":"ref21","first-page":"1","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Patton"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-847"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383533"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205757"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref29","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3989\/loquens.2014.006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101747"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10153"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref37","article-title":"SingMOS: An extensive open-source singing voice dataset for MOS prediction","author":"Tang","year":"2024","journal-title":"arXiv:2406.10911"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11746-1_40"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref41","first-page":"1","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-126"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633963"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3595353.3595883"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref47","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref49","first-page":"1","article-title":"The Blizzard Challenge 2021","volume-title":"Proc. Blizzard Challenge","author":"Ling"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref52","article-title":"Quality assessment of noisy and enhanced speech with limited data: UWB-NTIS system for VoiceMOS 2024 and beyond","author":"Kune\u0161ov\u00e1","year":"2025","journal-title":"arXiv:2506.00506"},{"key":"ref53","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40498-6_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64206-2_40"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00794-2_40"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27947-9_26"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11119540.pdf?arnumber=11119540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:46:16Z","timestamp":1755546376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11119540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3596644","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}