[music-dsp] perfect pitch shifter?

[Stephan M. Sprenger]

Paul Masri wrote:
> 
> > > Great examples. In fact i didn't even know how to imagine a > >perfect
> >pitch shift/time stretch of such a violin or a helicopter, > >even the
> >"perceptual transform" doesn't work here. So maybe it's > >even imposible
> >imagine/define a
> > >perfect pitch shifter.
> >[SNIP]
> >Now, this may seem impossible to approach but I think our brains are
> > >capable of doing this to a large extent.  For example, if you've >heard
> >enough violin notes then you can easily imagine different notes >played at
> >different pitches, on different strings and with different >volumes and
> >different bowing actions.  Therefore, advanced AI should >be able to learn
> >a synthesis technique from a set of examples and >then be able to re-sample
> >with parameter changes given an arbitary >input.
> 
> Sounds like a job for the resident Neural Network genius, Stephan
> Sprenger!!!

I feel flattered. Thanks a bunch, Paul... ;)

And yes, I think we all can do without Ebob here (right so r b-j?).

Stephan M.Sprenger
The DSP Dimension                           http://www.dspdimension.com

dupswapdrop -- the music-dsp mailing list and website: subscription info,
FAQ, source code archive, list archive, book reviews, dsp links
http://shoko.calarts.edu/musicdsp/