Classical algorithms of sound source localization with beamforming, TDOA and high-resolution spectral estimation.

A description of "RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization" [NeurIPS 2024]

The Official PyTorch Implementation of FN-SSL & IPDnet for Sound Source Localization [INTERSPEECH2023 & TASLP2024]

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

A python implementation of “SRP-DNN: Learning Direct-Path Phase Difference for Multiple Moving Sound Source Localization” [ICASSP 2022]

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

A python implementation of “Learning Deep Direct-Path Relative Transfer Function for Binaural Sound Source Localization” [TASLP 2021]

MATLAB Simulation Framework For Basic Sound Source Localization Using the GCC PHAT Algorithm

Test of the ability of a Convolutional Neural Network (CNN) trained to localize the Direction Of Arrival (DOA), to generalize in different environments.

A MATLAB implementation of “Multiple Sound Source Counting and Localization Based on TF-Wise Spatial Spectrum Clustering” [TASLP 2019]

[ICCV2023] Chaotic World: A Large and Challenging Benchmark for Human Behavior Understanding in Chaotic Events

3D Sound Source Localization using Masked Autoencoders

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

Localization of a sound source using a microphone array and beamforming technics

This scripts estimate Sound Source Position based on Cross-power Spectrum Phase (CSP) or Multiple Signal Classification (MUSIC).

PyTorch implementation of "Leveraging Category Information for Single-Frame Visual Sound Source Separation"

Eliminating Quantization Errors in Classification-Based Sound Source Localization

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

Projects webpage

This project develops an autonomous hexapod robot using auditory scene analysis for navigation. It integrates sound source localization (DOA) and beamforming via ODAS with a circular microphone array for precise spatial detection. A machine learning-based Keyword Spotting (KWS) module enables voice command recognition for human-robot interaction.