FastDiff 2: Revisiting and Incorporating GANs and Diffusion Models in High-Fidelity Speech Synthesis.
Rongjie HuangYi RenZiyue JiangChenye CuiJinglin LiuZhou ZhaoPublished in: ACL (Findings) (2023)
Keyphrases
- high fidelity
- speech synthesis
- diffusion models
- speech recognition
- diffusion model
- information diffusion
- text to speech
- social networks
- real time
- high quality
- medical image compression
- influence maximization
- viral marketing
- feature extraction
- information retrieval
- video conferencing
- edge detection
- probabilistic model