Filter by type:

Sort by year:

The Shape of RemiXXXes to Come: Audio texture synthesis with time–frequency scattering

Conference paper
Vincent Lostanlen, Florian Hecker
Proceedings of the International Conference on Digital Audio Effects (DAFx), 2019
Publication year: 2019

This article explains how to apply timefrequency scattering, a convolutional operator extracting modulations in the timefrequency domain at different rates and scales, to the re-synthesis and manipulation of audio textures.

Wavelet Scattering on the Pitch Spiral

Conference paper
Vincent Lostanlen, Stéphane Mallat
Proceedings of the International Conference on Digital Audio Effects (DAFx)
Publication year: 2015

We present a new representation of harmonic sounds that linearizes the dynamics of pitch and spectral envelope, while remaining stable to deformations in the timefrequency plane. It is an instance of the scattering transform, a generic operator which cascades wavelet convolutions and modulus nonlinearities. It is derived from the pitch spiral, in that convolutions are successively performed in time, log-frequency, and octave index. We give a closed-form approximation of spiral scattering coefficients for a nonstationary generalization of the harmonic sourcefilter model.

Transformée en scattering sur la spirale temps–chroma–octave

Conference paper
Vincent Lostanlen, Stéphane Mallat
Actes du colloque GRETSI, 2015
Publication year: 2015

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.

Joint Time–frequency Scattering for Audio Classification

Conference paper
Joakim Andén, Vincent Lostanlen, and Stéphane Mallat
Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
Publication year: 2015

We introduce the joint time–frequency scattering transform, a time shift invariant descriptor of time–frequency structure for audio classification. It is obtained by applying a two-dimensional wavelet transform in time and log-frequency to a time–frequency wavelet scalogram. We show that this descriptor successfully characterizes complex time–frequency phenomena such as time-varying filters and frequency modulated excitations. State-of-the-art results are achieved for signal reconstruction and phone segment classification on the TIMIT dataset.