Ivan Beskrovny's repositories
BlockchainMessenger
Information security project.
Chord-recognition
Chord recognition in songs using Viterbi algorithm - Wrote a Python code which takes any audio file and converts it into a chromogram. It then computes the distance matrix between features and template, further applying Viterbi algorithm to generate corresponding chords.
codec2
Open source speech codec designed for communications quality speech between 700 and 3200 bit/s. The main application is low bandwidth HF/VHF digital radio.
cwtlib
Continuous Wavelet Transform Library (CWTLib)
event_inviter
simple inviter for VK
Low-Speed-Vocoder
Algorithms of synthesis and decomposition for Russian speech at speed lower than 600 bits per second and algorithm of single input noise filtration, that was recorded with laryngophone during high noise (up to 110 dB).
musicstat
gathering info about music preferences of subscribers in VK
votebot
voting template using messages and keyboards in VK
deep-instrument-heroku
ML model to classify music instruments from audio - Heroku deployment.
distant_speech_recognition
spatial signal processing toolkit a.k.a beamforming toolkit 2.0 (BTK2.0)
DNS-Challenge
This repo contains the scripts, models, and required files for the ICASSP 2021 Deep Noise Suppression (DNS) Challenge.
infosec
Учебное пособие по защите информации кафедры радиотехники и систем управления МФТИ
LeetCode-Solutions
:octocat: Python / C++ 11 Solutions of All 974 LeetCode Problems (Weekly Update)
ml
Machine learning projects, often on audio datasets
spectral-subtraction
Spectral subtraction library
Spectral-Subtraction-1
Spectral Subtraction Python implementation.
Speech-Enhancement-Spectral-Subtraction
C implementation of spectral subtraction for speech enhancement
tensorflow
Computation using data flow graphs for scalable machine learning
VAD_VKtest
Test task for VK interview