Metraipolis › archive › dc_5230696ab9db
VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation — arXiv:2608.13613
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13613
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:30:42.954Z
- SHA-256 of the archived text
c429daf30a420df854ddc7a08fa546b09b50e5058662642f0d40f619f34d09ee- Stable URL of this page
https://metraipolis.com/documento/dc_5230696ab9db
How to cite
VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation — arXiv:2608.13613 — arXiv (en), https://arxiv.org/abs/2608.13613 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5230696ab9db (Metraipolis archive dc_5230696ab9db, sha256 c429daf30a420df854ddc7a08fa546b09b50e5058662642f0d40f619f34d09ee)
BibTeX
@misc{dc5230696ab9db,
title = {VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation — arXiv:2608.13613},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13613},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5230696ab9db; sha256 c429daf30a420df854ddc7a08fa546b09b50e5058662642f0d40f619f34d09ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13613. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent breakthroughs in generative models have made text-to-voice generation (TTV) possible, enabling the synthesis of speech directly from textual voice descriptions. However, existing systems face two key challenges. First, they struggle to generate a diverse range of voices, spanning real-world human speakers and fictional characters. Second, they lack robust and flexible voice editing capabilities, such as voice cloning and the ability to modify attributes like emotion and tone. In this paper, we propose VoiceDesigner, a unified framework for text-to-voice generation and editing that supports diverse and controllable voice design. To tackle the above challenges, we propose solutions from two perspectives. First, we develop a hybrid data pipeline that leverages digital signal processing techniques and speech generation models to construct a diverse voice dataset covering both real-world and fictional voices. Second, we introduce a diffusion transformer with architectural improvements to better handle complex conditioning and enhance multi-task performance, enabling unified voice generation and editing. Through subjective and objective evaluations, VoiceDesigner achieves superior prompt alignment with both voice descriptions and editing instructions, while maintaining competitive perceptual quality and voice usability compared to state-of-the-art TTV models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.13613 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T02:26:17.813Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).