Search Results for author: Jongmo Sung

Found 3 papers, 0 papers with code

Scalable and Efficient Neural Speech Coding: A Hybrid Design

no code implementations27 Mar 2021 Kai Zhen, Jongmo Sung, Mi Suk Lee, Seungkwon Beak, Minje Kim

We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine.

Quantization

Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding

no code implementations31 Dec 2020 Kai Zhen, Mi Suk Lee, Jongmo Sung, SeungKwon Beack, Minje Kim

Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals.

Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding

no code implementations18 Jun 2019 Kai Zhen, Jongmo Sung, Mi Suk Lee, Seung-Kwon Beack, Minje Kim

Speech codecs learn compact representations of speech signals to facilitate data transmission.

Cannot find the paper you are looking for? You can Submit a new open access paper.