{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:53Z","timestamp":1774419413124,"version":"3.50.1"},"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\/icassp49660.2025.10889119","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":0,"title":["SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis"],"prefix":"10.1109","author":[{"given":"Helin","family":"Wang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,USA"}]},{"given":"Jiarui","family":"Hai","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Yuchen","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Rilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Beijing,China"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref2","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","volume":"162","author":"Casanova"},{"key":"ref3","first-page":"1399","article-title":"A3t: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"International Conference on Machine Learning","volume":"162","author":"Bai"},{"key":"ref4","article-title":"Enhancing zero-shot text-to-speech synthesis with human feedback","volume":"abs\/2406.00654","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref5","article-title":"Soundstorm: Efficient parallel audio generation","volume":"abs\/2305.09636","author":"Borsos","year":"2023","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.741"},{"key":"ref7","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":"ref8","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems","author":"Le"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1392"},{"key":"ref10","article-title":"Neural codec language models are zero-shot text to speech synthesizers","volume":"abs\/2301.02111","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref11","article-title":"Uniaudio: Towards universal audio generation with large language models","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190717"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414633"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/a15050155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448134"},{"key":"ref18","article-title":"Proactive detection of voice cloning with localized watermarking","volume-title":"Forty-first International Conference on Machine Learning","author":"Roman"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447112"},{"key":"ref22","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref23","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Kreuk"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34703"},{"key":"ref29","article-title":"The curious case of neural text degeneration","volume-title":"8th International Conference on Learning Representations","author":"Holtzman"},{"key":"ref30","article-title":"Pheme: Efficient and conversational speech generation","volume":"abs\/2401.02839","author":"Budzianowski","year":"2024","journal-title":"CoRR"},{"key":"ref31","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","volume":"202","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389718"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-534"}],"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\/10889119.pdf?arnumber=10889119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:45Z","timestamp":1774416165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889119","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}