Search Results for author:
Found 2 papers, 0 papers with code
Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds
A differentiable digital signal processing (DDSP) autoencoder is a musical sound synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis.
Monaural source enhancement maximizing source-to-distortion ratio via automatic differentiation
At this time, we use an objective function that numerically expresses the quality of a mapping by DNN.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
