mkurop Goto Github PK
Name: Marcin Kuropatwiński
Type: User
Company: Talking 2 Rabbit
Location: Gdańsk
Name: Marcin Kuropatwiński
Type: User
Company: Talking 2 Rabbit
Location: Gdańsk
Aberth Method, a root-finding algorithms for simultaneous approximation of all the roots of a univariate polynomial.
A simple C++ library for reading and writing audio files.
Spliting an arrangement of 3D boxes into disjoint boxes
Composite measure of speech qualilty from the book by Philipos Loizou "Speech Enhancement - Theory and Practice"
Counting monomials with even exponents in a trace of a matrix raised to power
Illustration of CUDA expression templates/meta programming
Cutting a wave file containing speech into shorter fragments of required length. Uses speech pauses as cut points.
Encryption and decryption using openssl with ssh-keygen generated rsa key pair. Uses hybrid cryptography.
Classical Expectation-Maximization based Gaussian mixtures models training on CPU or GPU.
Algorithm for turning bayesian graph or factor graph into junction tree.
kaldi-asr/kaldi is the official location of the Kaldi project.
KMeans algorithm for computing a codebook based on training set - uses NumPy or CuPy.
Functions for running kmeans++ algorithm, either on CPU or GPU
Class for computing the Levenshtein distance and the three kinds of errors: insertions, deletions, and substitutions
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
Fast nonstationary noise tracking by Q. Zhang et al.
Noise tracking algorithm developed by Richard Hendriks
Fast nonstationary noise tracking algorithm by Q. Zhang et al. - coded in Matlab/Octave.
Implementation of the ITU P.56 active speech RMS power and active speech factor measurement.
Memory efficient tables of arbitrary size numbers from a given range.
My SpaceVim configuration init.toml file for turning it into Python IDE.
Documentation of the algorithm for finding a region of the high probability of a given 2-dimensional pdf.
Extended Kalman filter for denoising autoregressive (AR) proces, e.g. speech, contaminated by noise, also an AR process.
Classes for performing analysis and synthesis based on the Short Term Predictor/Long Term Predictor (STP/LTP) speech signal model. This speech signal model originates from the speech coding paradigm known as the Code Excited Linear Prediction (CELP).
Voice activity detection based on Sohn's algorithm with noise tracking by Zhang.
Voice activity detection by Sohn coded in python.
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.