{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:28:56Z","timestamp":1759332536114,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447722","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1451-1455","source":"Crossref","is-referenced-by-count":2,"title":["Selecting N-Lowest Scores for Training MOS Prediction Models"],"prefix":"10.1109","author":[{"given":"Yuto","family":"Kondo","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"1998","key":"ref1","article-title":"Method for objective measurements of perceived audio quality (PEAQ)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851924"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"issue":"6","key":"ref5","article-title":"Perceptual objective listening quality assessment (POLQA), the third generation ITU-T standard for end-to-end speech quality measurement part I I\u2014perceptual model","volume":"61","author":"Beerends","year":"2013","journal-title":"J. AES"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref7"},{"article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov","key":"ref8"},{"article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. ICML","author":"Qian","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. ICLR","author":"Popov","key":"ref11"},{"article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","volume-title":"Proc. NIPS End-to-end Learning for Speech and Audio Processing Workshop","author":"Patton","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-407"},{"article-title":"MB-Net: MOS prediction for synthesized speech with mean-bias network","volume-title":"Proc. IEEE ICASSP","author":"Leng","key":"ref16"},{"article-title":"LD-Net: Unified listener dependent modeling in MOS prediction for synthetic speech","volume-title":"Proc. IEEE ICASSP","author":"Huang","key":"ref17"},{"year":"1996","key":"ref18","article-title":"Methods for subjective determination of transmission quality"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/11491-005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"article-title":"UTMOS: Utokyo-Sarulab System for Voice-MOS Challenge 2022","volume-title":"Proc. Interspeech","author":"Saeki","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.10.003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref31"},{"issue":"1","key":"ref32","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume-title":"JMLR","volume":"15","author":"Srivastava"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447722.pdf?arnumber=10447722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:34:44Z","timestamp":1722573284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447722","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}