Multimedia Technologies Unit

Automated-GuitarAmpModelling

denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

ELFW

Developing code on semantic segmentation for Extended Labeled Faces in the Wild

libmysofa

Reader for AES SOFA files to get better HRTFs

minstrel

Minstrel is a FLOSS hybrid reading app specifically designed for Audio-eBooks

multimedia-eurecat.github.io

Open source code of the Multimedia Technologies Unit (MTU) website

Neuromuse

Code used for experiments conducted in Neuromuse

new-project

New project creation guidelines

PTS

Repository for Panningtable Synthesis

SMS

Repository for Spatial Matrix Synthesis

multimedia-eurecat/ELFW

Developing code on semantic segmentation for Extended Labeled Faces in the Wild

multimedia-eurecat/multimedia-eurecat.github.io

Open source code of the Multimedia Technologies Unit (MTU) website

multimedia-eurecat/PTS

Repository for Panningtable Synthesis

multimedia-eurecat/Automated-GuitarAmpModelling

multimedia-eurecat/denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

multimedia-eurecat/libmysofa

Reader for AES SOFA files to get better HRTFs

multimedia-eurecat/minstrel

Minstrel is a FLOSS hybrid reading app specifically designed for Audio-eBooks

multimedia-eurecat/Neuromuse

Code used for experiments conducted in Neuromuse

multimedia-eurecat/new-project

New project creation guidelines

multimedia-eurecat/SampleRNN

Tensorflow implementation of SampleRNN

multimedia-eurecat/SMS

Repository for Spatial Matrix Synthesis

multimedia-eurecat/phase-iv-ai-workshop1