Saurabh's repositories
deep_complex_networks
Implementation related to the Deep Complex Networks
Face-Detection-Tracking-and-Clustering
We detect and track faces in video, then extract features from those face tracks and try to cluster them into given number of persons.
handson-ml
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
improvedsegan
This repository is an extension of GAN based speech enhancement called SEGAN, and we present two modifications to make model training more robust and stable.
jsalt-2019-mt-tutorial
MT Tutorial for the JSALT 2019 Summer School
JSALT19-GluonNLP
JSALT 2019 Montréal: Dive into Deep Learning for Natural Language Processing
jsalt2019-diadet
Repository of recipes for the JSALT2019 workshop on "Speaker Detection in Adverse Scenarios with a Single Microphone"
latex-resumes
A collection of latex resume templates
Matlab-toolbox-for-DNN-based-speech-separation
This folder contains Matlab programs for a toolbox for supervised speech separation using deep neural networks (DNNs).
PRMLT
Pattern Recognition and Machine Learning Toolbox
Quadruplets-Network
Implementation of the Quadruplets Network and Quadruplets Loss as described in "Beyond triplet loss: a deep quadruplet network for person re-identification" .
rnn-speech-denoising
Recurrent neural network training for noise reduction in robust automatic speech recognition
segan-pytorch
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452
segan-tfworked
Speech Enhancement Generative Adversarial Network
segan_pytorch
Speech Enhancement Generative Adversarial Network in PyTorch
speech-denoising-wavenet
A neural network for end-to-end speech denoising
SpeechDenoisingWithDeepFeatureLosses
Speech Denoising with Deep Feature Losses
speedtest-cli
Command line interface for testing internet bandwidth using speedtest.net
tensorflow-workshop
This repo contains materials for use in a TensorFlow workshop.
unimatrix
Python script to simulate the display from "The Matrix" in terminal. Uses half-width katakana unicode characters by default, but can use custom character sets. Accepts keyboard controls while running. Based on CMatrix.
Wave-U-Net-For-Speech-Enhancement
Improved speech enhancement with the Wave-U-Net. Applying Stoller et al's deep convolutional neural network architecture to speech enhancement in the time-domain.