Re: IPA speech synthesizer

2009/2/19 Arnt Richard Johansen <arj@...>:
> This is, unfortunately, orders of magnitude more difficult to do than speech
> synthesis for a specific language. :-(
>
> I could write a lengthy essay on why this is impossible (or at least a
> Herculean task), but the short version is as follows: the individual segments
> in a speech stream affect each other so much that you can't just splice
> together phones and get a result that sounds like speech.
A solution! Just get a good fluid simulator and model airflow in a human mouth.

So it requires a $100,000 solver and a supercomputer and a year to get
to "Hello", but it's worth it.

Or choose a reasonable subset of the IPA to support.