Research Projects Archives - Page 4 of 4

Bitwise Source Separation on Hashed Spectra

[latexpage] A common approach to source separation is to estimate a masking matrix that can classify each pixel of an Short-Time Fourier Transform (STFT) of the mixture signal into the…

minje February 26, 2020

Research Projects

Learning to Hash for Source Separation

[latexpage] We have cared much about the efficiency of the machine learning inference process. As a part of this effort, we recently came up with a hash code-based source separation…

minje February 8, 2020

Research Projects

Lightweight End-to-End Speech Enhancement

Machine guns Models-5dB+5dB Input Mixture Gated ResNet DenseNet Dilated DenseNet DenseNet+GRU Proposed Clean Speech Cicadas Models-5dB+5dB Input Mixture Gated ResNet DenseNet Dilated DenseNet DenseNet+GRU Proposed Clean Speech Motorcycles Models-5dB+5dB Input…

minje February 8, 2020

Research Projects

Collaborative Deep Learning

For the general introduction to personalized speech enhancement (PSE), please read this article: Personalized Speech Enhancement. Our dream is to develop a universal speech enhancement system that can deal with all…

minje July 31, 2019

Featured Projects Research Projects

Neural Pitch Correction of Singing Voice

Have you ever wished if you were a good singer? Some people believe that it’s a natural ability that one can never acquire by practice (like my wife who’s a…

minje July 31, 2019

Research Projects

Cross-Module Residual Learning for Neural Audio Coding

Speech/audio coding has traditionally involved substantial domain-specific knowledge such as speech generation models. If you haven’t heard of this concept, don’t worry, because you might be using this technology in…

minje July 31, 2019