[IAEP] Reading (was Re: changes in outlook with Sugar
echerlin at gmail.com
Sat Jul 4 16:34:21 EDT 2009
On Sat, Jul 4, 2009 at 12:08 PM, Gary C Martin<gary at garycmartin.com> wrote:
> Hi Jim,
> On 4 Jul 2009, at 17:09, Jim Simmons wrote:
>> I think you have an interesting idea here. It reminded me of the
>> scene in _2001 A Space Odyssey_ where Hal 9000 is having the higher
>> functions of his brain disconnected and he tries to sing "Daisy" while
>> he still has enough connected to do it. From my experience working
>> with espeak I'd say that getting a computer to sing, even badly, may
>> be beyond what we can reasonably do today.
It has been done. Google 「computer sing」 . But that doesn't matter for
the purpose of Same-Language Subtitling of videos of people singing,
or a karaoke program with text synched to MP3s.
>> Espeak can speak at
>> different pitches and rates, but I don't think you can change pitch
>> and rate while speech is going on and if you could that's still a long
>> way off from actual singing.
> Not convinced it would make a viable solution for Sugar but...
> There's a speech synth called Festival (actually developed by Edinburgh
> University, my old Uni). It does support a singing mode, but others have
> extended it more completely. Here's some MIDI generated samples from flinger
> (festival singer):
September 07, 2007
Make Your Computer Sing With Festival
> A few yeas back a colleague of mine was involved in a gallery art
> installation that used (I think) 4 Mac minis mounted on a wall, and a small
> back room server to parse incoming junk mail. The Mac minis then sang out
> some of that text content realtime :-)
Silent Thunder (默雷/धर्ममेघशब्दगर्ज/دھرممیگھشبدگر ج) is my name
And Children are my nation.
The Cosmos is my dwelling place, The Truth my destination.
http://earthtreasury.org/worknet (Edward Mokurai Cherlin)
More information about the IAEP