Skip to main content
Open Access Publications from the University of California

Cooperative Learning of Deep Generative Models with Application in Sound Synthesis

  • Author(s): Zhong, Ruiqi
  • Advisor(s): Wu, Ying Nian
  • et al.

Fires, rainstorms or insect swarms produce natural sounds made up of rapidly occurring

acoustic events. which we call ”sound textures”. This kind of phenomena have been studied

by computational audio community [MS11] and neural science people for a long time. From

previous studies, it has been verified that sound textures can be schematically synthesized

from statistical models fairly well. Here we take a novel approach involving neural networks

or deep learning methods. Specifically, we use cooperative training of a descriptor and a

generator network, modeled as a convolutional neural network(ConvNet) and a deconvolu-

tional neural network(DeconvNet) respectively. From several experiments, we proved that

our framework can capture the essence of sound textures and synthesize identifiable natural


Main Content
Current View