LMA feedback in MiM #5
Unanswered
musicinmotion-dev
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
The model is always trying to identify a gesture-based on what I trained it with. This makes it keen on going to certain positions rather than gradually shifting…
It looks like it’s heavy on the loudness side, meaning that when using loudness that feature feels stronger than the sensory inputs.
It’s also hard to know because I need to record a new set of data when I change the feature set.
It is hard to set the LMA values in forehand and then record them.
Also if I make three good ones and the fourth is not so good I have to start over or live with it…
But it can definitely already detect a gesture that I recorded when playing it after training. I also get quite good values of for example indirect space effort when improvising music with a lot of legato feeling where I also am moving from side to side witch it a feature that I’ve seen with most clarinettists.
Beta Was this translation helpful? Give feedback.
All reactions