San Francisco, Oct 2 : Google has created a new machine learning tool called Tone Transfer that allows people to transform every sound like whistling into something like a violin, or a saxophone, or a flute.
“We created a tool called Tone Transfer to allow musicians and amateurs alike to tap into DDSP (Differentiable Digital Signal Processing) as a delightful creative tool,” Nida Zada, UX Lead, Google Research, wrote in a blog post on Thursday.
Developed by Google Research’s Magenta team, the process can lead to many creative, quirky results.
For example, one can try replacing a capella singing with a saxophone solo, or a dog barking with a trumpet performance.
“This development is important because it enables music technologies to become more inclusive,” Zada said.
Machine learning models inherit biases from the datasets they are trained on, and music models are no different.
Rather than following the formal rules of western music, like the 12 notes on a piano, DDSP transforms sound by modelling frequencies in the audio itself.
This opens up machine learning technologies to a wider range of musical cultures, Zada said.