jweissman
Joined 13 years ago
Joined 13 years ago
- My strongest suggestion is finding some strategy for smoothing over the sometimes harsh-sounding edge of the sample window - Perhaps it could be filling in/passing over segments of what is sounded to user as a larger loop? Both giving it a larger window to articulate things but maybe also showcasing the interpolation more clearly… - Tone control may seem challenging but I do wonder if you couldn’t “tune” the output of the model as a whole somehow (given the spectrogram format it could be a translation/scale knob potentially?)
a few thoughts:
- it would be nice to go "the other direction" here too -- from a set of chords, tell me the possible ambient key environments
- the only thing ux wise i can pick at is the squiggly underline
- support for modulation would be amazing (a basic query there might be just "find any/all common chords between two selected key environments")