FFT-Based Acoustic Beamforming on Streaming Microphone Arrays
Overview
What this challenge is about.
Implement overlap-add streaming FFT (FFTW or KissFFT) processing 64 channels × 1024-sample frames with 50 percent overlap. Apply delay-and-sum beamforming across a 2D direction-of-arrival (DoA) grid (180 × 90 azimuth × elevation, 2-degree resolution). Output a per-frame DoA heatmap. Validate against three labeled fault recordings: report DoA accuracy (degrees from ground truth) and sustained throughput on a Raspberry Pi 4 reference device. Deliver C++ reference, a Python validation notebook, and a 6-page methodology + benchmark report.
The Brief
What you'll do, and what you'll demonstrate.
Build an FFT-based delay-and-sum beamformer that processes a 64-channel 48 kHz microphone array in real time on an embedded ARM device.
Earning criteria — what you'll demonstrate
- Apply overlap-add FFT for streaming spectral analysis
- Implement delay-and-sum beamforming with sub-sample steering vectors
- Validate DoA accuracy against labeled ground truth
- Optimize FFT pipelines for ARM embedded targets
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.