Skip to main content

Feedback Recurrent Autoencoder

Yang Yang, Guillaume Sautière, Jongha Ryu, Taco Cohen

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
    Length: 12:18
04 May 2020

In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency. The recurrent structure of FRAE is designed to efficiently extract the redundancy along the time dimension and allows a compact discrete representation of the data to be learned. We demonstrate its effectiveness in speech spectrogram compression. Specifically, we show that the FRAE, paired with a powerful neural vocoder, can produce high-quality speech waveforms at a low, fixed bitrate. We further show that by adding a learned prior for the latent space and using an entropy coder, we can achieve an even lower variable bitrate.

Value-Added Bundle(s) Including this Product

More Like This

  • SPS
    Members: $150.00
    IEEE Members: $250.00
    Non-members: $350.00
  • SPS
    Members: $150.00
    IEEE Members: $250.00
    Non-members: $350.00
  • SPS
    Members: $150.00
    IEEE Members: $250.00
    Non-members: $350.00