Speech Synthesis and Control Using Differentiable DSP
Giorgio Fabbro, Vladimir Golkov, Thomas Kemp, Daniel Cremers
The paper will soon be available on arXiv.
Clip 1
| Clip | Audio | Download Link |
|---|---|---|
| Original Audio | Download | |
| WaveGlow (no control possible) | Download | |
| Our Model (original pitch) | Download | |
| Our Model (pitch shift) | Download | |
| Our Model (constant pitch) | Download | |
| Our Model (ramp up added to original pitch) | Download | |
| Our Model (original pitch modulated with sinusoid) | Download |