Skip to Main content Skip to Navigation
Conference papers

Comparing Representations for Audio Synthesis Using Generative Adversarial Networks

Abstract : 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Gaël RICHARD Connect in order to contact the contributor
Submitted on : Monday, May 24, 2021 - 3:40:40 PM
Last modification on : Wednesday, April 13, 2022 - 5:32:02 PM
Long-term archiving on: : Wednesday, August 25, 2021 - 6:07:58 PM


Files produced by the author(s)




Javier Nistal Hurlé, Stefan Lattner, Gael Richard. Comparing Representations for Audio Synthesis Using Generative Adversarial Networks. 2020 28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam (virtual), France. pp.161-165, ⟨10.23919/Eusipco47968.2020.9287799⟩. ⟨hal-03233340⟩



Record views


Files downloads