{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:54:29Z","timestamp":1777128869448,"version":"3.51.4"},"reference-count":35,"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\/icassp49660.2025.10888907","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["SPSinger: Multi-Singer Singing Voice Synthesis with Short Reference Prompt"],"prefix":"10.1109","author":[{"given":"Junchuan","family":"Zhao","sequence":"first","affiliation":[{"name":"National University of Singapore,School of Computing,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chetwin","family":"Low","sequence":"additional","affiliation":[{"name":"National University of Singapore,School of Computing,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore,School of Computing,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"236","DOI":"10.18653\/v1\/2023.findings-acl.16","article-title":"RMSSinger: Realistic-music-score based singing voice synthesis","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"He","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903099"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-119"},{"key":"ref6","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3394769"},{"key":"ref8","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"Gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1789"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054636"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682656"},{"key":"ref14","article-title":"Expressive singing synthesis using local style token and dual-path pitch encoder","author":"Lee","year":"2022"},{"key":"ref15","article-title":"Mr-svs: Singing voice synthesis with multi-reference encoder","author":"Wang","year":"2022"},{"key":"ref16","article-title":"Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jiang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","first-page":"21450","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023","volume":"202","author":"Liu","year":"2023"},{"key":"ref21","first-page":"17022","article-title":"Hifi-gan: 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":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037956"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref25","article-title":"A unified model for zero-shot singing voice conversion and synthesis","volume-title":"Ismir 2022 Hybrid Conference","author":"Wu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054582"},{"key":"ref27","article-title":"Magic Data Technology Co., Ltd","year":"2019"},{"key":"ref28","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Ren"},{"key":"ref29","first-page":"6914","article-title":"M4singer: A multi-style, multi-singer and musical score provided mandarin singing corpus","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref31","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095655"},{"key":"ref35","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\/10888907.pdf?arnumber=10888907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:56Z","timestamp":1774416176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888907","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}