Name: Satvik Venkatesh
Type: User
Company: University of Plymouth, UK
Bio: I am pursuing a PhD at ICCMR. My research interests include Deep Learning, Brain-Computer Interfaces, and Unconventional Computing for music.
Twitter: SatvikVenkatesh
Satvik Venkatesh's Projects
Artificially synthesising data for audio segmentation to improve music-speech detection
This is a repository for computer programs written during the CAMT503 module
This is a tutorial on using data generators with Keras for audio classification.
This repository is associated with the blog post on "Data Generators with Keras and Tensorflow on Google Colab"
Domestic environment sound event detection task
This repository allows you to load sound files and extract embeddings from them through VGGish.
A repository for JUCE tutorials
Hyperparameter tuning for humans
Open-Unmix - Music Source Separation for PyTorch
This repository comprises audio and MIDI files composed by the author and Physarum polycephalum for the song called 'Creep into my Lawn'.
Single and multichannel sound event detection using convolutional recurrent neural networks. DCASE 2017 real-life sound event detection winning method.
A single page website theme
SinglePaged - Simple Jekyll template
Sound analysis/synthesis tools for music applications
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Deezer source separation library including pretrained models.
Training Set Synthesis for Audio Segmentation and Classification of Music and Speech in Radio Broadcast
General Speech Restoration
(work in progress) recreation of a bell / waterphone instrument with GUI and sound synthesis
Implementation of the Wave-U-Net for audio source separation
Improved Wave-U-Net implemented in Pytorch
This repository implements the Wave-U-net architecture in TensorFlow 2
Using Word embeddings for automatic EQ mixing