[DECtalk] Question About Formant vs Natural Speech

[Don]

On 6/19/2022 6:52 AM, joshknnd1982 at gmail.com wrote:
> Actually, vocalizer is unit-selection speech and I think the new neural-tts
> voices like alexa may be hmm-based speech, hmm or h-m-m means hidden Markov
> model.

And what do you think the "units" are?  :>