Variable Bitrate Discrete Neural Representations via Causal Self-Attention

By Shuyang Li, Huanru Henry Mao, Julian McAuley. 2021

Subfields: Generative Models, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Yossi Adi
2. Jade Copet
3. Alexandre D'efossez
4. Gabriel Synnaeve

In Model Architectures

1. Jade Copet
2. Alexandre D'efossez
3. Gabriel Synnaeve
4. Yossi Adi

Citations in the corpus

• High Fidelity Neural Audio Compression (2022, background): “Following Zeghidour et al. (2021); Li et al. (2021), we use C = 32, B = 4 and (2, 4, 5, 8) as strides.”