Search Results for author:
Found 5 papers, 3 papers with code
Instabilities in Convnets for Raw Audio
Numerical simulations align with our theory and suggest that the condition number of a convolutional layer follows a logarithmic scaling law between the number and length of the filters, which is reminiscent of discrete wavelet bases.
Fitting Auditory Filterbanks with Multiresolution Neural Networks
Waveform-based deep learning faces a dilemma between nonparametric and parametric approaches.
Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
The paper uses a frame-theoretic setting to study the injectivity of a ReLU-layer on the closed ball of $\mathbb{R}^n$ and its non-negative part.
Separating and denoising seismic signals with dual-path recurrent neural network architecture
We show that separation is possible also for seismic recordings, using techniques from machine learning (and even those recorded with a single sensor).<br />This may have an impact on seismic applications such as <br />ambient noise tomography, induced seismicity, earthquake analysis, aftershock analysis, nuclear verification, and seismoacoustics/infrasound.<br />The machine learning technique that we use for seismic signal separation is based on a dual-path recurrent neural network which is applied directly to the time domain data.
Inpainting of long audio segments with similarity graphs
We present a novel method for the compensation of long duration data loss in audio signals, in particular music.
