{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:55:40Z","timestamp":1777128940892,"version":"3.51.4"},"reference-count":25,"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\/icassp49660.2025.10889751","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference"],"prefix":"10.1109","author":[{"given":"Shuqi","family":"Dai","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunyun","family":"Wang","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roger B.","family":"Dannenberg","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Jin","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref2","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Bigvgan: A universal neural vocoder with large-scale training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lee"},{"key":"ref4","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448232"},{"key":"ref10","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref12","article-title":"Nansy++: Unified voice synthesis with neural analysis and synthesis","author":"Choi","year":"2022"},{"key":"ref13","volume-title":"Softvc vits singing voice conversion"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447981"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389711"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681642"},{"key":"ref17","article-title":"Music style transfer: A position paper","volume-title":"Proceedings of 6th International Workshop on Musical Metacreation","author":"Dai"},{"key":"ref18","article-title":"A unified model for zero-shot singing voice conversion and synthesis","volume-title":"Ismir 2022 Hybrid Conference","author":"Wu"},{"key":"ref19","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref21","article-title":"Ddsp: Differentiable digital signal processing","volume-title":"International Conference on Learning Representations","author":"Engel"},{"key":"ref22","first-page":"12449","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":"ref23","article-title":"Singstyle111: A multilingual singing dataset with style transfer","volume-title":"Proc. of the 24th Int. Society for Music Information Retrieval Conf","author":"Dai"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref25","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"}],"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\/10889751.pdf?arnumber=10889751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:18Z","timestamp":1774416138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889751","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}