Abstract: Although the vision transformer-based methods (ViTs) exhibit an excellent performance than convolutional neural networks (CNNs) for image recognition tasks, their pixel-level semantic ...
DisCoder is a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results