{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:42:57Z","timestamp":1777657377203,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832295","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"803-810","source":"Crossref","is-referenced-by-count":24,"title":["The Voicemos Challenge 2024: Beyond Speech Quality Prediction"],"prefix":"10.1109","author":[{"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"NVIDIA,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute Of Information And Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryandhimas E.","family":"Zezario","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2023-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626267"},{"key":"ref10","article-title":"SelfSupervised Speech Quality Estimation and Enhancement Using Only Clean Speech","volume-title":"Proc. ICLR","author":"Fu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.002"},{"key":"ref12","article-title":"Singmos: An extensive open-source singing voice dataset for mos prediction","author":"Tang","year":"2024","journal-title":"arXiv preprint arXiv:2406.10911"},{"key":"ref13","first-page":"835","article-title":"Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm","volume-title":"ITU-T recommendation","year":"2003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2023-2"},{"key":"ref15","article-title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","author":"Leglaive","year":"2024","journal-title":"arXiv preprint arXiv:2402.01413"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205757"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10597"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref34","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeruIPS","author":"Baevski"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref37","first-page":"25","article-title":"BYOL-S: Learning self-supervised speech representations by bootstrapping","volume-title":"HEAR: Holistic Evaluation of Audio Representations (NeurIPS 2021 Competition).","volume":"13","author":"Elbanna"},{"key":"ref38","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"in Proc. ICML","author":"Radford"},{"key":"ref39","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref41","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. ICML, 2021","author":"Tan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-851"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832295.pdf?arnumber=10832295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:18Z","timestamp":1737398358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832295","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}