John Martinsson

DMEL: The Differentiable Log-Mel Spectrogram as a Trainable Layer in Neural Networks

In this paper we present the differentiable log-Mel spectrogram (DMEL) for audio classification. DMEL uses a Gaussian window, with a window length that can be jointly optimized with the neural network. DMEL is used as the input layer in different neural networks and evaluated on standard audio datas…