But the title makes it seem like the algorithm is synthesizing the sounds from scratch!
But the title makes it seem like the algorithm is synthesizing the sounds from scratch!
It does. If you read the paper, they say that first they went with matching sounds from a database, but later turned on to full synthesis.
Reference: look for "parametric synthesis" in the paper https://arxiv.org/pdf/1512.08512v2.pdf
> where the stick moved similarly
where the stick moved similarly and was hitting similar things, which is a non-trivial task.
But that's also the approach of current speech synthesis algorithms and works better than trying to create the waveform from scratch.
I don't think it's that simple. Speech synthesis by concatenation does produce more natural-sounding results, at least until you notice its quirks, so casual users tend to prefer it. But I know some heavy speech synthesis users, specifically blind programmers and power-users, and they tend to prefer parametric synthesis, because it's more intelligible at high speeds.