no code implementations • 14 Nov 2023 • Haici Yang, Inseon Jang, Minje Kim
In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network.
no code implementations • 14 Mar 2023 • Darius Petermann, Inseon Jang, Minje Kim
Spectral sub-bands do not portray the same perceptual relevance.
no code implementations • 16 Nov 2022 • Seokjin Lee, Minhan Kim, Seunghyeon Shin, Daeho Lee, Inseon Jang, Wootaek Lim
Recently, the realtime audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis.
no code implementations • 25 May 2021 • Daniela N. Rim, Inseon Jang, Heeyoul Choi
We apply a reparametrization trick for the Bernoulli distribution for the discrete representations, which allows smooth backpropagation.