Transformée en scattering sur la spirale temps-chroma-octave

09/01/2015
by   Vincent Lostanlen, et al.
0

We introduce a scattering representation for the analysis and classification of sounds. It is locally translation-invariant, stable to deformations in time and frequency, and has the ability to capture harmonic structures. The scattering representation can be interpreted as a convolutional neural network which cascades a wavelet transform in time and along a harmonic spiral. We study its application for the analysis of the deformations of the source-filter model.

READ FULL TEXT
research
01/03/2016

Wavelet Scattering on the Pitch Spiral

We present a new representation of harmonic sounds that linearizes the d...
research
05/01/2018

Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties

We present a machine learning algorithm for the prediction of molecule p...
research
07/20/2020

wav2shape: Hearing the Shape of a Drum Machine

Disentangling and recovering physical attributes, such as shape and mate...
research
12/17/2019

CNN-Based Invertible Wavelet Scattering for the Investigation of Diffusion Properties of the In Vivo Human Heart in Diffusion Tensor Imaging

In vivo diffusion tensor imaging (DTI) is a promising technique to inves...
research
03/07/2019

A Learnable ScatterNet: Locally Invariant Convolutional Layers

In this paper we explore tying together the ideas from Scattering Transf...
research
11/24/2020

Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks

We introduce an end-to-end deep learning architecture called the wide-ba...
research
07/17/2023

Riesz feature representation: scale equivariant scattering network for classification tasks

Scattering networks yield powerful and robust hierarchical image descrip...

Please sign up or login with your details

Forgot password? Click here to reset