Paper Info
Title
Classification with Joint Time-Frequency Scattering.
Abstract
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.
Year
Venue
Field
2018
arXiv: Sound
Convolutional neural network,Computer science,Convolution,Network architecture,Algorithm,Speech recognition,Scattering,Invariant (mathematics),Chirp,Time–frequency analysis,Wavelet
DocType
Volume
Citations 
Journal
abs/1807.08869
2
PageRank 
References 
Authors
0.38
17
3
Name
Order
Citations
PageRank
Joakim Andén1647.70
vincent lostanlen2278.88
Stéphane Mallat31109.92