#🔊 AEC PBFDAF Baseline
This repository provides a real-time acoustic echo cancellation (AEC) baseline based on a Partitioned Block Frequency-Domain Adaptive Filter (PBFDAF).
The implementation is designed for research, benchmarking, and educational purposes, emphasizing measurable behavior and real-time constraints.
##🔑 Key Features
- Real-time PBFDAF-based adaptive filtering
- Double-talk detection
- Online ERLE measurement and convergence statistics
- Clear separation between core processing and GUI control
This project prioritizes clarity and correctness over product-level optimizations.
This repository is provided as a baseline and research reference for acoustic echo cancellation using PBFDAF.
If you use this codebase, architecture, or ideas in:
- Academic publications
- Theses
- Technical reports
- Blog posts
- Derivative implementations
Please cite or clearly acknowledge this repository.
This repository is intended to be referenced as a baseline, not rebranded as an original end-to-end AEC system.
###✔️ Suggested Citation
isinmelih. AEC PBFDAF Baseline: Research-oriented implementation of partitioned-block frequency-domain adaptive filtering for acoustic echo cancellation. GitHub repository, 2026.
Share feedback & improvements on metrics & performance plots → Click here
The latest precompiled binaries for aec-pbfdaf-baseline are available on GitHub Releases.
Download and run the ZIP package:
Latest Release v0.1
The ZIP contains:
wasapi_aec.exe(core engine)control_panel.exe(GUI launcher)README.mdwith usage instructions- Example metrics / performance plots (if included)
##📝 Usage Notes
- This project is not intended to claim novelty or state-of-the-art performance
- Designed for learning, evaluation, and controlled experimentation
- Modifications and extensions should be clearly documented by downstream users
- While the Apache 2.0 license permits reuse, ethical academic practice requires transparent attribution