11 May
2014
11 May
'14
12:45 p.m.
[Florian Paul Schmidt]
And so on.. Also for a usable guitar synthesizer one
would maybe have
to go a step further. The closer one is to the onset of the note the
more uncertain the pitch is (loosely and much simplified speaking: for
a low note it takes quite a while until even half a cycle has passed -
during that time the pitch is very uncertain), so one approach would
be to use a percussive sound for the start of the note (onset
detection is easier than pitch detection I would figure) and then once
the pitch is established fade to a second synthesis model that
produces a clearly defined pitch.
Mapping this to a midi stream introduces some loss of information, but
could also be possible (e.g. two midi outs, one for the percussive
onset detection and one for the (slower) pitch detection).
I wanted to try this for a long time.. Maybe using decent machine
learning and lots of training data one could even identify the pitch
based on the characteristics of the very early signal from a note, but
I'm not really certain about that.
I think (haven't found the time to read relevant papers, work out the
details or even implement anything so take it cum grano salis) that it
should be possible to speed up note detection by training pattern
recognition to harmonics.
While the fundamental takes some time to detect in the lower
registers, harmonics are a lot faster and their patterns strongly hint
at the fundamental frequency. There's quite a bit of variation in
harmonic patterns of guitar notes due to picking method, string gauge,
fret wire and for electric guitar pickup position and design etc.
which could make the approach infeasible, but I think it's worth
looking into this as you'll only have to deal with partially
attenuated harmonics, not entirely different patterns.
Cheers, Tim
PS: I can do quick recordings of a few scales on electric guitar for
you if you like, with reasonable rhythmic accuracy but no textual
description to go along with it.