{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:48:17Z","timestamp":1776883697711,"version":"3.51.2"},"reference-count":55,"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\/asru65441.2025.11434730","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Robust Training of Singing Voice Synthesis Using Prior and Posterior Uncertainty"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Zhao","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yuxun","family":"Tang","sequence":"additional","affiliation":[{"name":"Renmin University of China"}]},{"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref3","first-page":"4009","article-title":"Vocaloid-commercial singing synthesizer based on sample concatenation","volume":"2007","author":"Kenmochi","year":"2007","journal-title":"Interspeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019362"},{"key":"ref5","article-title":"Design of an interactive virtual reality system for ensemble singing","volume-title":"Interactive Audio Systems Symposium","author":"Kearney"},{"key":"ref6","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","author":"Kingma"},{"key":"ref8","article-title":"Denoising diffusion implicit models","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Song"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053512"},{"key":"ref10","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","volume":"abs\/2407.05407","author":"Du","year":"2024","journal-title":"CoRR"},{"key":"ref11","article-title":"Seed-music: A unified framework for high quality and controlled music generation","author":"Bai","year":"2024"},{"key":"ref12","article-title":"Inspiremusic: Integrating super resolution and large language model for high-fidelity long-form music generation","author":"Zhang","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-978"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-33"},{"key":"ref15","article-title":"Synthio: Augmenting small-scale audio classification datasets with synthetic data","author":"Ghosh","year":"2024","journal-title":"arXiv preprint arXiv:2410.02056"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.268"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/slt61566.2024.10832313"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.140"},{"key":"ref23","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10799952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1410"},{"key":"ref28","article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","volume-title":"CoRR","volume":"abs\/2009.01776","author":"Chen","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-391"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref33","article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","volume-title":"ICLR","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747422"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101327"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref38","first-page":"2796","article-title":"Accurate uncertainties for deep learning using calibrated regression","volume-title":"International conference on machine learning","author":"Kuleshov"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1040"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_14"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_31"},{"key":"ref44","first-page":"7559","article-title":"Differentiable augmentation for data-efficient gan training","volume":"33","author":"Zhao","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2970919"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685000"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"key":"ref48","article-title":"Decoupled weight decay regularization","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","author":"Loshchilov"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref50","article-title":"Ofuton-p singing voice corpus","year":"2020"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2025.naacl-demo.19","article-title":"VERSA: A versatile evaluation toolkit for speech, audio, and music","volume-title":"2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics - System Demonstration Track","author":"Shi"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832289"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref55","article-title":"Mos-bench: Benchmarking generalization abilities of subjective speech quality assessment models","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv:2411.03715"}],"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\/11434730.pdf?arnumber=11434730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:57Z","timestamp":1775192337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434730","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}