Did you read section 3 of the paper where they evaluate their system?

> We primarily rely on crowdsourced Mean Opinion Score (MOS) evaluations based on subjective listening tests. All our MOS evaluations are aligned to the Absolute Category Rating scale [14], with rating scores from 1 to 5 in 0.5 point increments. We use this framework to evaluate synthesized speech along two dimensions: its naturalness and similarity to real speech from the target speaker.

They're testing if the generated speech sounds natural with a well-defined and reproducible experiment. That's science.