{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:07Z","timestamp":1776886387423,"version":"3.51.2"},"reference-count":52,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434769","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Layer-wise Analysis for Quality of Multilingual Synthesized Speech"],"prefix":"10.1109","author":[{"given":"Erica","family":"Cooper","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}]},{"given":"Yamato","family":"Ohtani","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","author":"Kong","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref5","article-title":"Methods for subjective determination of transmission quality","year":"1996","journal-title":"ITU-T Rec. P.800"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-32"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10922"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094909"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref14","first-page":"862","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","journal-title":"ITU-T Recommendation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref16","article-title":"Evaluation of contextual descriptors for HMM-based speech synthesis in French","volume-title":"Eighth ISCA Workshop on Speech Synthesis","author":"Maguer"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095710"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1675"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref21","article-title":"Self-supervised speech quality estimation and enhancement using only clean speech","author":"Fu","year":"2024","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832178"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626267"},{"key":"ref24","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref28","article-title":"High fidelity speech synthesis with adversarial networks","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski"},{"key":"ref29","first-page":"173","article-title":"Deep Speech 2: end-to-end speech recognition in English and Mandarin","volume-title":"International conference on machine learning","author":"Amodei"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-938"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref32","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10714935"},{"key":"ref36","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688047"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101747"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref40","article-title":"XIMERA: A new TTS from ATR based on corpus-based technologies","volume-title":"Fifth ISCA Workshop on Speech Synthesis","author":"Kawai"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10633"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2013-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3451951"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref45","volume-title":"The LJ Speech dataset","author":"Ito","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"key":"ref48","volume-title":"Recommendation P.56: Objective measurement of active speech level"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-969"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3515206"}],"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\/11434769.pdf?arnumber=11434769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:34Z","timestamp":1775192374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434769","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}