Whoa—what an eerie, funky thing to undertake: using a computer to anticipate a specific person’s idiosyncratic (yet predictable!) hand gestures based just on a recording of their speech:
Now they just need to automatically add accordions.
As for the training data:
Our speakers come from a diverse set of backgrounds: television show hosts, university lecturers and televangelists. They span at least three religions and discuss a large range of topics from commentary on current affairs through the philosophy of death, chemistry and the history of rock music, to readings in the Bible and the Qur’an.
As always, “This is the strangest life I’ve ever known…”