DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech
D DuplexGen is presented, a dialogue synthesis framework that explicitly decouples content, timing, and acoustics and produces conversational dynamics closer to the real-dialogue reference distribution than the stitching baselines evaluated in this study.
Pengcheng Wang, Sheng Li, JiyiLi et al.
· 0 citations