[MUD-Dev] online voice communication

[Hans-Henrik Staerfeldt]

On Wednesday 27 November 2002 02:53, Amanda Walker wrote:
> On 11/25/02 5:11 AM, Daniel.Harman at barclayscapital.com
> <Daniel.Harman at barclayscapital.com> wrote:

>> I've yet to hear any text to speech that wasn't immediately
>> recognisable as such, and certain to get grating after only a few
>> seconds having to listen to it.

> http://www.cepstral.com/ (disclaimer: the CEO is an old classmate
> of mine) Or check out some of the examples for the "Festival"
> voice synthesis package.  If you can track the pitch and prosody
> of a real human speaking the text, you can get *much* more natural
> than having to simulate it from a text-to-speech model.

> People teach themselves to read Elvish and Klingon, so why not? :-)

This is the best speech synthesis i have found yet (with respect to
quality, not diversity) is;
 
  http://www.naturalvoices.com/

--
Hans Henrik Stærfeldt   |    bombman at diku.dk    | work:  hhs at cbs.dtu.dk      |
Address:                |___  +45 40383492    __|__       +45 45252471     __|
DTU, Kemitorvet,        | Scientific programmer at Center for Biological     |
bygn 208, CBS.          |  Sequence Analysis, Technical University of Denmark|


_______________________________________________
MUD-Dev mailing list
MUD-Dev at kanga.nu
https://www.kanga.nu/lists/listinfo/mud-dev