etzinis Goto Github PK
Name: Efthymios Tzinis
Type: User
Company: Google LLC
Bio: Research Scientist @Google
Twitter: ETzinis
Location: Cambridge, MA, USA
Blog: https://etzinis.com/
Name: Efthymios Tzinis
Type: User
Company: Google LLC
Bio: Research Scientist @Google
Twitter: ETzinis
Location: Cambridge, MA, USA
Blog: https://etzinis.com/
Active Learning for Emotionally Salient Utterances and Segments using Text & Audio
Pytorch-based audio source separation toolkit || Current highlight : the new recipe for Microsoft's DNS Challenge !
Code for the paper: Unified Gradient Reweighting for Model Biasing with Applications to Source Separation
Bootstrapped MDS: A Coordinate Search Algorithm for Multidimensional Scaling which optimizes Stress by evaluating the function multiple times over different coordinates but also bootstraping over previous successful iterations. With this algorithm there is a probability of evaluating the function alongside a coordinate step depending on the previous successful evaluations across this coordinate.
Labs exercises in NTUA (2016-2017) for the Computer Vision course 8th semester Contributors: Efthymios Tzinis Konstantinos Kallas
Code for the paper: Separate but togerher: Unsupervised Federated Learning for Speech Enhancement from non-iid data
Check the GPUs status on multiple servers
Code and data recipes for the paper: Heterogeneous Target Speech Separation
Latex Code of thesis tools for manipulation
Labs exercises in NTUA (2015-2016) for the course Microprocessors 7th semester. Contributors: Efthymios Tzinis, Anastasis Stathopoulos, Rafail Skoulos
Convolutional Neural Decomposition for End2End Speech Emotion Recognition
Evaluating Nonlinear dimensional reduction algorithms for finding low dimensional manifold representations of input data, trying to infer labels of unlabelled data points of the manifold as well as visualizing 2D manifolds for qualitative analysis of the input data
Non linear dynamics for emotion classification
Labs exercises in NTUA (2016-2017) for Neural Networks course 9th semester Contributors: Efthymios Tzinis Konstantinos Kallas
Code and data recipes for the paper: Optimal Condition Training for Target Source Separation by Efthymios Tzinis, Gordon Wichern, Paris Smaragdis and Jonathan Le Roux
Labs exercises in NTUA (2016-2017) for Operating Systems Laboratory course 8th semester. Contributors: Efthymios Tzinis & Kostantinos Kallas
Labs exercises in NTUA (2016-2017) for the Pattern Recognition course 9th semester Contributors: Efthymios Tzinis Konstantinos Kallas
Pattern Search MDS algorithm implementation
My exercises in NTUA (2015-2016) for the course Programming Languages 6th semester (C,Java,ML,Prolog)
Code for my contribution in a medicine related project/paper with faculty form Kapodistrian University of Athens.
Unified Complex Network and Recurrence Analysis Toolbox
Labs exercises in NTUA (2015-2016) for the course Speech and Natural Language Processing 7th semester
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
Various teaching assistant's (TA) tools for automating processes with grading, assigning students, etc.
A simple prompt/recorder preparation tool for questions 1&2 in TOEFL examination (speaking section)
A two step optimization for sound source separation on the adaptive front-end domain
Unsupervised domain adaptation for conversational speech enhancement using RemixIT
Code for the paper: "Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information"
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.