L-SpEx
L-SpEx copied to clipboard
gemengtju
L-SpEx: Localized Target Speaker Extraction
The data configuration and simulation of L-SpEx. The code scripts will be released in the future.
Data Generation:
-
Download LibriSpeech(dev-clean.tar.gz, test-clean.tar.gz, train-clean-100.tar.gz, train-clean-360.tar.gz) and Wham_noise(wham_noise.zip). And move the librispeech and wham_noise to 'data_simulation/MC-Libri2Mix/spatilize_mixture/'
-
generate the RIRs information.
python run_sample_reverb_libri.py
- generate the MC-Libri2Mix dataset using RIRs information.
./generate_librimix.sh YOUR_SAVE_PATH
NOTE: you can also download the generated MC-Libri2Mix dataset by using this dropbox link (Download)
Environments:
python: 3.8.3
Pytorch: 1.6
gemengtju