GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models.
Matthew BaasHerman KamperPublished in: SLT (2022)
Keyphrases
- speech synthesis
- diffusion models
- bandwidth allocation
- diffusion model
- speech recognition
- quality of service
- text to speech
- information diffusion
- social networks
- vocal tract
- allocation scheme
- influence maximization
- application layer
- viral marketing
- video on demand
- greedy algorithm
- social network analysis
- language model
- website
- computer vision
- anisotropic diffusion
- diffusion process
- real time
- communication networks
- resource allocation
- motion estimation
- machine learning