A Python toolkit for sound source separation.

Combine sound source separation with SRP-PHAT to achieve multi-source localization.

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Official codebase for "Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling".

Official Codebase of "A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition" (ICML 2023)

Implements the DUET blind source separation algorithm. MATLAB code from here - https://github.com/yvesx/casa495

Code for the paper: Visually Guided Sound Source Separation using Cascaded Opponent Filter Network

Projects webpage

Visualising Sound