Tone/Timbre Transfer - interesting ML thing from Google
Tone/Timbre Transfer - interesting ML thing from Google
This seems like a new thing in audio processing. https://sites.research.google/tonetransfer
I want to turn birdsong into a 303 line.
Through that link you can only choose to turn your inout audio into a flute, sax, trumpet or violin. But there is a version on Colab that apparently allows you to upload your own models - https://colab.research.google.com/githu ... wg1WkHCXQO - though I haven't yet worked out how to make a model. Should have plenty of time for that in tier 2 lockdown.Tone Transfer uses machine learning models to transform sounds into musical instruments used in a variety of styles, from Baroque to jazz. Rerender the chirp of a bird into a flute. Turn a cello piece into a saxophone solo. Tone Transfer makes these transformations possible through a new ML technique called Differentiable Digital Signal Processing, or DDSP.
I want to turn birdsong into a 303 line.