DeepAI AI Chat
Log In Sign Up

Comparing Representations for Audio Synthesis Using Generative Adversarial Networks

by   Javier Nistal, et al.

In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the experiments on a subset of the NSynth dataset. The architecture follows the benchmark Progressive Growing Wasserstein GAN. We perform experiments both in a fully non-conditional manner as well as conditioning the network on the pitch information. We quantitatively evaluate the generated material utilizing standard metrics for assessing generative models, and compare training and sampling times. We show that complex-valued as well as the magnitude and Instantaneous Frequency of the Short-Time Fourier Transform achieve the best results, and yield fast generation and inversion times. The code for feature extraction, training and evaluating the model is available online.


page 1

page 2

page 3

page 4


Adversarial Generation of Time-Frequency Features with application in audio synthesis

Time-frequency (TF) representations provide powerful and intuitive featu...

Signal Representations for Synthesizing Audio Textures with Generative Adversarial Networks

Generative Adversarial Networks (GANs) currently achieve the state-of-th...

StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

In this paper we introduce StyleWaveGAN, a style-based drum sound genera...

GANSynth: Adversarial Neural Audio Synthesis

Efficient audio synthesis is an inherently difficult machine learning ta...

Adversarial Audio Synthesis with Complex-valued Polynomial Networks

Time-frequency (TF) representations in audio synthesis have been increas...

Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations

The high temporal resolution of audio and our perceptual sensitivity to ...

VQCPC-GAN: Variable-length Adversarial Audio Synthesis using Vector-Quantized Contrastive Predictive Coding

Influenced by the field of Computer Vision, Generative Adversarial Netwo...