IEEE

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

Abstract: 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 ...
IEEE

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Abstract: Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream ...