GitHub - barrelorgandiscovery/fftmusings: Project applying neural networks to audio data, in particular, attempting to train an LSTM to recognize and reproduce music based on raw music samples. Uses FFT/Phase Vocoder for input followed by an autoencoder and then an LSTM with a mixture density cost function to model the sequence of data.

barrelorgandiscovery / fftmusings Public

forked from jarney/fftmusings

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Project applying neural networks to audio data, in particular, attempting to train an LSTM to recognize and reproduce music based on raw music samples. Uses FFT/Phase Vocoder for input followed by an autoencoder and then an LSTM with a mixture density cost function to model the sequence of data.