Preprint
Aug 2026
Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling
DAIEN-TTS is presented, an environment-aware zero-shot TTS framework that disentangles and jointly models speech, background noise, and reverberation, enabling independent control over timbre and acoustic environment through separate speaker and environment prompts.
Ye-Xin Lu, Xin Wang, Yang Ai et al.
· 0 citations