Book Image

Hands-On Generative Adversarial Networks with PyTorch 1.x

By : John Hany, Greg Walters
Book Image

Hands-On Generative Adversarial Networks with PyTorch 1.x

By: John Hany, Greg Walters

Overview of this book

With continuously evolving research and development, Generative Adversarial Networks (GANs) are the next big thing in the field of deep learning. This book highlights the key improvements in GANs over generative models and guides in making the best out of GANs with the help of hands-on examples. This book starts by taking you through the core concepts necessary to understand how each component of a GAN model works. You'll build your first GAN model to understand how generator and discriminator networks function. As you advance, you'll delve into a range of examples and datasets to build a variety of GAN networks using PyTorch functionalities and services, and become well-versed with architectures, training strategies, and evaluation methods for image generation, translation, and restoration. You'll even learn how to apply GAN models to solve problems in areas such as computer vision, multimedia, 3D models, and natural language processing (NLP). The book covers how to overcome the challenges faced while building generative models from scratch. Finally, you'll also discover how to train your GAN models to generate adversarial examples to attack other CNN and GAN models. By the end of this book, you will have learned how to build, train, and optimize next-generation GAN models and use them to solve a variety of real-world problems.
Table of Contents (15 chapters)
Free Chapter
1
Section 1: Introduction to GANs and PyTorch
5
Section 2: Typical GAN Models for Image Synthesis

Speech quality enhancement with SEGAN

In Chapter 7, Image Restoration with GANs, we explored how GANs can restore some of the pixels in images. Researchers have found a similar application in NLP where GANs can be trained to get rid of the noises in audio in order to enhance the quality of the recorded speeches. In this section, we will learn how to use SEGAN to reduce background noise in the audio and make the human voice in the noisy audio more audible.

SEGAN architecture

Speech Enhancement GAN (SEGAN) was proposed by Santiago Pascual, Antonio Bonafonte, and Joan Serrà in their paper, SEGAN: Speech Enhancement Generative Adversarial Network. It uses 1D convolutions to successfully remove noise from speech audio. You...