• Corpus ID: 235265897

High Resolution Time-Frequency Generation with Generative Adversarial Networks

  title={High Resolution Time-Frequency Generation with Generative Adversarial Networks},
  author={Zeynel Deprem and A. Enis cCetin},
—Signal representation in Time-Frequency (TF) do- main is valuable in many applications including radar imaging and inverse synthetic aparture radar. TF representation allows us to identify signal components or features in a mixed time and frequency plane. There are several well-known tools, such as Wigner-Ville Distribution (WVD), Short-Time Fourier Transform (STFT) and various other variants for such a purpose. The main requirement for a TF representation tool is to give a high-resolution… 

Figures and Tables from this paper

Cross-term-free time–frequency distribution reconstruction via lifted projections

An l1 minimization approach based on projections onto convex sets is proposed to obtain a high-resolution, cross-term-free TF distribution for a given signal, and it is proposed that this approach does not require any parameter adjustment.

Deep multi-scale video prediction beyond mean square error

This work trains a convolutional network to generate future frames given an input sequence and proposes three different and complementary feature learning strategies: a multi-scale architecture, an adversarial training method, and an image gradient difference loss function.

Generative Image Modeling Using Style and Structure Adversarial Networks

This paper factorize the image generation process and proposes Style and Structure Generative Adversarial Network, a model that is interpretable, generates more realistic images and can be used to learn unsupervised RGBD representations.

Image-to-Image Translation with Conditional Adversarial Networks

Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.


In this second part of the paper the Wigner distribution is adapted to the case of discrete-time signals. It is shown that most of the properties of this time-frequency signal representation carry

Time-frequency convolutional networks for robust speech recognition

  • V. MitraH. Franco
  • Computer Science
    2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)
  • 2015
This work presents a modified CDNN architecture that is called the time-frequency convolutional network (TFCNN), in which two parallel layers of convolution are performed on the input feature space: convolution across time and frequency, each using a different pooling layer.

Time-Frequency Reassignment: From Principles to Algorithms

This chapter discusses time–frequency analysis from a second generation perspective, where what is discussed here essentially builds on the methods that have already been extensively studied and used.

Conditional Generative Adversarial Nets

The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

An adaptive optimal-kernel time-frequency representation

The time-frequency representation presented here, based on a signal-dependent radially Gaussian kernel that adapts over time, tracks signal component variations over time and supports online implementation for signals of arbitrary length is presented.