christhetree

mod_extraction

Source code for "Modulation Extraction for LFO-driven Audio Effects".

CPP_Directed_Acyclic_Graph

C++ implementation of a directed acyclic graph. Written for maximum execution speed, therefore avoiding the new operator whenever possible and allocating memory only once.

serum_rnn

DeepLearningForBela

jtfst_implementation

Differentiable, GPU-accelerated implementation of the Joint Time-Frequency Scattering Transform.

Android_Yellow_Pages_App_TDD

Android app using Yellow Pages API and Google Maps API. Developed using TDD, robolectric testing framework & roboguice dependency injection; very high test code coverage.

residual_audio

webmushra_video

webMUSHRA Video: a MUSHRA testing framework for videos.

Android_Yellow_Pages_App_Content_Provider

Android app using Yellow Pages API and Google Maps API. Includes complete use of fragments, factories, database/tables and most importantly integration of a content provider to manage all data related actions.

h_dqn

Implementation of h-DQN.

sr_invariant_conv

Experiments for a sampling rate (SR) invariant convolution for audio data.

Android_Echo_Bluetooth

Echo with bluetooth syncing.

Android_Parallelism

Initial tests and prototypes of the Parallelism Android app.

CPP_Double_Hash_Table

C++ implementation of a double hashed hash table.

auraloss

Collection of audio-focused loss functions in PyTorch

CPP_Dynamic_Cyclic_Queue

C++ implementation of a dynamic cyclic queue.

CPP_Lazy_Deletion_Binary_Tree

C++ implementation of a lazy deletion binary tree.

ddsp-phaser

Echo

Calhacks app.

fadtk

A simple library for Fréchet Audio Distance (FAD) calculation

neutone_sdk

personal_latex_template

pymushra

pyMUSHRA is a python web application which hosts webMUSHRA experiments and collects the data with python.

RenderMan

Command line C++ and Python VSTi Host library with MFCC, FFT, RMS and audio extraction and .wav writing.

scrapl-ddsp

Scattering with Random Paths as Loss for DDSP

serum_rnn_website

torchlpc

torchsynth

A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.