CookVoice framework unifies speech and singing voice generation

Researchers have introduced CookVoice, a unified framework designed for controllable multi-modal human voice generation. This system separates voice into content, prosody, and style factors, enabling it to handle tasks such as text-to-speech, singing voice generation, and voice editing within a single model. CookVoice demonstrates comparable generation quality to existing systems while offering enhanced style and prosody control, and it achieves this with a relatively small parameter count and efficient inference. AI

IMPACT This unified framework could streamline development and improve control for various voice generation applications.

RANK_REASON The cluster contains an academic paper detailing a new framework for voice generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• CookVoice
• DagsHub
• Gotit.pub
• Hugging Face
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →