{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:38Z","timestamp":1775199998679,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015641","name":"Tateisi Science and Technology Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015641","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434711","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Sampling-Frequency Naturalness MOS Prediction Using Self-Supervised Learning Model with Sampling-Frequency-Independent Layer"],"prefix":"10.1109","author":[{"given":"Go","family":"Nishikawa","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Wataru","family":"Nakata","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Kanami","family":"Imamura","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Tomohiko","family":"Nakamura","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"NaturalSpeech 3: zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju"},{"key":"ref2","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","volume-title":"Proc. ICLR","author":"Siuzdak"},{"key":"ref3","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389788"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NIPS","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3203907"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/116.20230082"},{"key":"ref14","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume-title":"Proc. NeurIPS","author":"Tancik"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco58844.2023.10289819"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref22","article-title":"The road less scheduled","volume-title":"Proc. NeurIPS","author":"Defazio"},{"key":"ref23","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. ICLR","author":"Liu"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434711.pdf?arnumber=11434711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:40Z","timestamp":1775192320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434711","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}