{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:10Z","timestamp":1776888610745,"version":"3.51.2"},"reference-count":26,"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\/icassp49660.2025.10889279","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Evidential-TTS: High Fidelity Zero-Shot Text-to-Speech Using Evidential Deep Learning"],"prefix":"10.1109","author":[{"given":"Myeonghun","family":"Jeong","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minchan","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Semin","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023"},{"key":"ref2","article-title":"Vampnet: Music generation via masked acoustic token modeling","volume-title":"Ismir 2023 Hybrid Conference","author":"Garcia"},{"key":"ref3","article-title":"Masked audio generation using a single non-autoregressive transformer","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ziv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3381910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-465"},{"key":"ref10","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Forty-first International Conference on Machine Learning","author":"Ju"},{"key":"ref11","article-title":"Predictive uncertainty estimation via prior networks","volume":"31","author":"Malinin","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref13","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"International Conference on Machine Learning","author":"Chang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_5"},{"key":"ref15","article-title":"Evidential deep learning to quantify classification uncertainty","volume":"31","author":"Sensoy","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00213"},{"key":"ref17","article-title":"Reverse kl-divergence training of prior networks: Improved uncertainty and adversarial robustness","volume":"32","author":"Malinin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref21","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"P-flow: a fast and data-efficient zero-shot tts through speech prompting","volume":"36","author":"Kim","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref25","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak super-vision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"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\/10889279.pdf?arnumber=10889279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:27:06Z","timestamp":1774416426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889279","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}