wesbz Goto Github PK

followers: 50.0 following: 89.0 repos: 41.0 gists: 0.0

Name: Wes Bouaziz

Type: User

Bio: Graduated: 🎓 Computer Science @ CentraleSupélec 🎓 Maths & Machine Learning @ ENS Paris-Saclay Previously interned @ ENS Paris 💻 & Facebook AI Research 💻

Twitter: _vassim

Location: Paris' suburb

Hi there, I'm Wassim (Wes for short) 👋

🔭 I’m currently working on Speech Processing, Music Processing, Graph Machine Learning.
🌱 I’m currently learning JAX
👯 I’m looking to collaborate on cool research projects
💬 Ask me about anything!
😄 Pronouns: he/him
⚡ Fun fact: I like skateboarding 🛹, playing piano 🎹 and guitar 🎸.

Currently listening 🎧 🎼

Top Tracks
Short term	Medium term	Long term

Based on natemoo-re's README

Languages and tools

Versionning

Programming Languages

Libraries

Content Design

Wes Bouaziz's Projects

arrayfire

ArrayFire: a general purpose GPU library.

banditagents

Implementations of known algorithms for the bandit problem

cs-188-pacman-practice

Practice for a course using Berkeley's CS-188 resources

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.