Skip to content

mrjunjieli/LRS3_for_AVSS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

Instruction for generating data for AVSS

Before run this script, you need to install dlib first.

You can follow this blog to install.

This script is only for LRS3 dataset. You need to rewrite something for other datasets.

you need to modify path to your own path before running.

Step 1 Audio process

  1. extract audio
cd audio_process 
./extract_audio.sh
  1. (optional) cut audio of some speakers to 4~6 s
./audio_cut.sh 
  1. generate text file of mixed audio
python audio_path.py
  1. mix audio. This code refers to Deep Clustering
/opt18/matlab_2015b/bin/matlab -nosplash -nodesktop -r create_wav_2speakers

Step 2 Video process

  1. extract frames
cd video_process 
./extract_frames.sh
  1. generate file_path_of_frame and save it to LRS3_image.scp
by yourself
  1. detect and crop face + lip regions
python extrac_face_and_lip.py
  1. convert image sequences to npy
python convert_npy.py 

Thanks for KaiLi, This script is based on his repo

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published