• Corpus ID: 238226825

An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution

  title={An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution},
  author={James King and Ramon Vinas Torn'e and Alexander Campbell and Pietro Lio'},
There have been several successful deep learning models that perform audio superresolution. Many of these approaches involve using preprocessed feature extraction which requires a lot of domain-specific signal processing knowledge to implement. Convolutional Neural Networks (CNNs) improved upon this framework by automatically learning filters. An example of a convolutional approach is AudioUNet, which takes inspiration from novel methods of upsampling images. Our paper compares the pre… 

Figures and Tables from this paper

Improved Estimation of Leaf Wetness Duration Using Deep-Learning-Based Time-Resolution Technique

Plant diseases are one of the leading causes of the loss of crops. Monitoring the plant growth conditions could help prevent the spread of diseases and ensure healthy agricultural productivity. A

Bandwidth Extension on Raw Audio via Generative Adversarial Networks

This work explores a GAN-based method for audio processing, and develops a convolutional neural network architecture to perform audio super-resolution, using an autoencoder-based loss that enables training in the GAN framework, with feature losses derived from unlabeled data.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

Synthesizing Audio with Generative Adversarial Networks

WaveGAN is introduced, a first attempt at applying GANs to raw audio synthesis in an unsupervised setting and it is found that human judges prefer the generated examples from WaveGAN over those from a method which naively apply GAns on image-like audio feature representations.

Enhanced Deep Residual Networks for Single Image Super-Resolution

This paper develops an enhanced deep super-resolution network (EDSR) with performance exceeding those of current state-of-the-art SR methods, and proposes a new multi-scale deepsuper-resolution system (MDSR) and training method, which can reconstruct high-resolution images of different upscaling factors in a single model.

Image Super-Resolution Using Deep Convolutional Networks

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.

Audio Super Resolution using Neural Networks

A new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks, and demonstrates the effectiveness of feed-forward Convolutional architectures on an audio generation task.

Improved Training of Wasserstein GANs

This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.

Arbitrary Scale Super-Resolution for Brain MRI Images

This paper proposes a new network that combines that technique with SRGAN, a state-of-the-art GAN-based architecture, to achieve arbitrary scale, high fidelity Super-Resolution for medical images, and shows that performance across scales is not compromised, and that it is able to achieve competitive results with other state of theart methods such as EDSR whilst being fifty times smaller than them.

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.