{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:09Z","timestamp":1775230089434,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887675","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Mean Opinion Scores in Speech Quality Assessment: Score Aggregation through Quantized Distribution Fitting"],"prefix":"10.1109","author":[{"given":"Yuto","family":"Kondo","sequence":"first","affiliation":[{"name":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[{"name":"NTT Corporation,Communication Science Laboratories,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref5","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref6","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref7","article-title":"GradTTS: 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","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref10","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. ICLR","author":"Popov"},{"key":"ref11","article-title":"Methods for subjective determination of transmission quality","year":"1996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447722"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715419"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02559-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2527"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1243"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1285"},{"key":"ref22","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":"ref23","article-title":"Validity of mos from the perspective of psychological measurement theory and the future direction of subjective evaluation for synthetic speech","author":"Kishida","year":"2024","journal-title":"J. ASJ"},{"key":"ref24","article-title":"A software package for sequential quadratic programming","author":"Kraft","year":"1988","journal-title":"Forschungsbericht- Deutsche Forschungs- und Versuchsanstalt fur Luftund Raumfahrt"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/13.1.25"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1037\/11491-005"},{"key":"ref28","article-title":"Here or There: Preference Judgments for Relevance","volume-title":"Proc. ECIR","author":"Carterette"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1076"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887675.pdf?arnumber=10887675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:42Z","timestamp":1774416402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887675","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}