Classification with Joint Time-Frequency Scattering

07/24/2018
by   Joakim andén, et al.
0

In time series classification, signals are typically mapped into some intermediate representation which is used to construct models. We introduce the joint time-frequency scattering transform, a locally time-shift invariant representation which characterizes the multiscale energy distribution of a signal in time and frequency. It is computed through wavelet convolutions and modulus non-linearities and may therefore be implemented as a deep convolutional neural network whose filters are not learned but calculated from wavelets. We consider the progression from mel-spectrograms to time scattering and joint time-frequency scattering transforms, illustrating the relationship between increased discriminability and refinements of convolutional network architectures. The suitability of the joint time-frequency scattering transform for characterizing time series is demonstrated through applications to chirp signals and audio synthesis experiments. The proposed transform also obtains state-of-the-art results on several audio classification tasks, outperforming time scattering transforms and achieving accuracies comparable to those of fully learned networks.

READ FULL TEXT
research
12/07/2015

Joint Time-Frequency Scattering for Audio Classification

We introduce the joint time-frequency scattering transform, a time shift...
research
10/18/2015

Clustering Noisy Signals with Structured Sparsity Using Time-Frequency Representation

We propose a simple and efficient time-series clustering framework parti...
research
06/13/2020

Interpretable Super-Resolution via a Learned Time-Series Representation

We develop an interpretable and learnable Wigner-Ville distribution that...
research
07/25/2023

Fitting Auditory Filterbanks with Multiresolution Neural Networks

Waveform-based deep learning faces a dilemma between nonparametric and p...
research
02/15/2022

Phase-Based Signal Representations for Scattering

The scattering transform is a non-linear signal representation method ba...
research
06/21/2019

The Shape of RemiXXXes to Come: Audio Texture Synthesis with Time-frequency Scattering

This article explains how to apply time-frequency scattering, a convolut...
research
07/20/2020

wav2shape: Hearing the Shape of a Drum Machine

Disentangling and recovering physical attributes, such as shape and mate...

Please sign up or login with your details

Forgot password? Click here to reset