etzinis Goto Github PK

activelearning

Active Learning for Emotionally Salient Utterances and Segments using Text & Audio

asteroid

Pytorch-based audio source separation toolkit || Current highlight : the new recipe for Microsoft's DNS Challenge !

biased_separation

Code for the paper: Unified Gradient Reweighting for Model Biasing with Applications to Source Separation

bootstrapped_mds

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.

comp_vision_ntua

Labs exercises in NTUA (2016-2017) for the Computer Vision course 8th semester Contributors: Efthymios Tzinis Konstantinos Kallas

etzinis.github.io

fedenhance

Code for the paper: Separate but togerher: Unsupervised Federated Learning for Speech Enhancement from non-iid data

gpus_utilization

Check the GPUs status on multiple servers

heterogeneous_separation

Code and data recipes for the paper: Heterogeneous Target Speech Separation

lathesis

Latex Code of thesis tools for manipulation

micro_lab_ntua

Labs exercises in NTUA (2015-2016) for the course Microprocessors 7th semester. Contributors: Efthymios Tzinis, Anastasis Stathopoulos, Rafail Skoulos

neural_demompose

Convolutional Neural Decomposition for End2End Speech Emotion Recognition

nldr_visual_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

nldrp

Non linear dynamics for emotion classification

nns_ntua

Labs exercises in NTUA (2016-2017) for Neural Networks course 9th semester Contributors: Efthymios Tzinis Konstantinos Kallas

optimal_condition_training

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

os_lab_ntua

Labs exercises in NTUA (2016-2017) for Operating Systems Laboratory course 8th semester. Contributors: Efthymios Tzinis & Kostantinos Kallas

pat_rec_ntua

Labs exercises in NTUA (2016-2017) for the Pattern Recognition course 9th semester Contributors: Efthymios Tzinis Konstantinos Kallas

pattern-search-mds

Pattern Search MDS algorithm implementation

pl_1

My exercises in NTUA (2015-2016) for the course Programming Languages 6th semester (C,Java,ML,Prolog)

polymorphisms_statistic_analysis

Code for my contribution in a medicine related project/paper with faculty form Kapodistrian University of Athens.

pyunicorn

Unified Complex Network and Recurrence Analysis Toolbox

speech_nlp_labs

Labs exercises in NTUA (2015-2016) for the course Speech and Natural Language Processing 7th semester

sudo_rm_rf

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.

ta_tools

Various teaching assistant's (TA) tools for automating processes with grading, assigning students, etc.

toefl_speaking

A simple prompt/recorder preparation tool for questions 1&2 in TOEFL examination (speaking section)

two_step_mask_learning

A two step optimization for sound source separation on the adaptive front-end domain

unsup_speech_enh_adaptation

Unsupervised domain adaptation for conversational speech enhancement using RemixIT

unsupervised_spatial_dc

Code for the paper: "Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information"