Krug, Paul K;
Birkholz, Peter;
Gerazov, Branislav;
Van Niekerk, Daniel R;
Xu, Anqi;
Xu, Yi;
(2023)
Self-Supervised Solution to the Control Problem of Articulatory Synthesis.
In:
Proceedings of the INTERSPEECH 2023.
(pp. pp. 4329-4333).
ISCA: Dublin, Ireland.
Preview |
Text
krug23_interspeech.pdf - Published Version Download (566kB) | Preview |
Abstract
Given an articulatory-to-acoustic forward model, it is a priori unknown how its motor control must be operated to achieve a desired acoustic result. This control problem is a fundamental issue of articulatory speech synthesis and the cradle of acousticto-articulatory inversion, a discipline which attempts to address the issue by the means of various methods. This work presents an end-to-end solution to the articulatory control problem, in which synthetic motor trajectories of Monte-Carlo-generated artificial speech are linked to input modalities (such as natural speech recordings or phoneme sequence input) via speakerindependent latent representations of a vector-quantized variational autoencoder. The proposed method is self-supervised and thus, in principle, synthesizer and speaker model independent.
Loading...
Loading...Loading...| 1. |  Germany | 18 |
| 2. |  United States | 16 |
| 3. |  United Kingdom | 12 |
| 4. |  Japan | 4 |
| 5. |  China | 3 |
| 6. |  India | 3 |
| 7. |  France | 2 |
| 8. |  Australia | 1 |
| 9. |  Palestinian Territory | 1 |
| 10. |  Spain | 1 |
Archive Staff Only
 |
View Item |
