A python implementation of “SRP-DNN: Learning direct-path phase difference for multiple moving sound source localization”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
Preparation
Training
python RunSRPDNN.py --train --gen-on-the-fly --gpu-id [*] (--use-amp)
Evaluation
python RunSRPDNN.py --test --gpu-id [*] --time 00000001 --eval-mode locata pred eval (--use-amp)
python RunSRPDNN.py --test --no-cuda --time 00000001 --eval-mode locata pred eval (--use-amp)
Pretrained models
If you find our work useful in your research, please consider citing:
@InProceedings{yang2022srpdnn,
author = "Bing Yang and Hong Liu and Xiaofei Li",
title = "SRP-DNN: Learning direct-path phase difference for multiple moving sound source localization",
booktitle = "Proceedings of {IEEE} International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
year = "2022",
pages = "721-725"}
MIT