Feedback Recurrent Autoencoder

Abstract

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.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyyang2019feedback

Related papers

• Disentangled Sequential Autoencoder (2018)0.00
• RAVE: A Variational Autoencoder For Fast And High-quality Neural Audio Synthesis (2021)0.00
• Harp-net: Hyper-autoencoded Reconstruction Propagation For Scalable Neural Audio Coding (2021)9.41
• Convolutional Variational Autoencoders For Spectrogram Compression In Automatic Speech Recognition (2024)0.00
• Deep Vocoder: Low Bit Rate Compression Of Speech With Deep Autoencoder (2019)5.24
• A Recurrent Variational Autoencoder For Speech Enhancement (2019)13.97
• Enhancing Into The Codec: Noise Robust Speech Coding With Vector-quantized Autoencoders (2021)10.21
• Codecslime: Temporal Redundancy Compression Of Neural Speech Codec Via Dynamic Frame Rate (2025)0.00