kentoo-zbcast / YOHO-on-VOICe

YOHO-on-VOICe

Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset (preprint)

VOICe Dataset Link, click here.

Instructions: 0. Install requirements.txt.

1. Set required parameters like sample_rate in config.py.
2. Download and extract the VOICe dataset in the data/9dB and data/3dB folder inside the VOICe/ folder.
3. Run python process_dataset.py.
4. Run python train.py --backend pytorch -e indoor -alr for running pytorch code.