Open TeeJayBaker opened 9 months ago
Copy the basic pitch convolution architecture taking in stacked harmonic CQT and freq encoding to output both a individual CQT and an MFCC
Target multiple objective functions, one being MSSL on the output spectrogram, and 2 being MFCC loss against the correct individual voice timbre.
Copy the basic pitch convolution architecture taking in stacked harmonic CQT and freq encoding to output both a individual CQT and an MFCC
Target multiple objective functions, one being MSSL on the output spectrogram, and 2 being MFCC loss against the correct individual voice timbre.