activity
20172022
most citedPsychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding

30 citations · 42 across the 18 of their papers we have counts for

collaborators

27 papers

eess.AS2022

The Potential of Neural Speech Synthesis-based Data Augmentation for Personalized Speech Enhancement

Anastasia Kuznetsova, Aswin Sivaraman, Minje Kim

With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic me…

eess.AS20221 cited

Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding

Haici Yang, Wootaek Lim, Minje Kim

Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features. This paper introduces additional coding…

eess.AS2022

Upmixing via style transfer: a variational autoencoder for disentangling spatial images and musical content

Haici Yang, Sanna Wager, Spencer Russell +3

In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results. In thi…

eess.AS2022

SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation

Darius Petermann, Minje Kim

With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem. While e…

eess.AS2021

HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

Darius Petermann, Seungkwon Beack, Minje Kim

An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder par…

eess.AS2021

Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization

Haici Yang, Shivani Firodiya, Nicholas J. Bryan +1

The task of manipulating the level and/or effects of individual instruments to recompose a mixture of recordings, or remixing, is common across a variety of applications such as mu…