Skip to content

Latest commit

 

History

History
65 lines (54 loc) · 2.67 KB

README.md

File metadata and controls

65 lines (54 loc) · 2.67 KB
Raw

Software supporting "Modeling Vocal Entrainment in Conversational Speech using Deep Unsupervised Learning"

original code by Md Nasir Modified for Python3 by Megh Krishnaswamy and Adarsh Pyrelal

Updated on June 3, 2022 (Work in Progress)

Scripts are written in Python 3.9

Dependencies and Requirements

  1. Bash
  2. OpenSMILE
  3. sph2pipe
  4. Kaldi
  5. LDC corpus and metadata files
    (for ToMCAT users, a small sample of the corpus is available at kraken.sista.arizona.edu:/media/mule/projects/ldc)
    note: move all files in the

Summary of directories and files

  • feat/ :- Directory containing scripts for acoustic feature extraction and functional computation
  • models/ :- Directory containing scripts for different deep unsupervised learning models for entrainment
  • utils/ :- Directory containing utility files used by other scripts

Files that need to be edited by user to add filepaths:

ToDo- edit this with latest files

  • ~~entrainment_config.py
  • ~~feats/run_all_nopre.sh
  • ~~models/NED/run_all_nopre.sh

Start Point:

ToDo- edit this for instructions for the makefile

  1. Setup and activate virtual environment
  2. Run pip install -e .
  3. To run the code on your system, download and set-up the LDC data, and access/create Fisher_meta.csv
    • scp -r [username]@kraken.sista.arizona.edu:/media/mule/projects/ldc [local directory]
  4. Add a step for setup.py, wheel and installing requirements
  5. ~~Ensure you have installed all required python libraries
  6. ~~Edit entrainment_config.py, feats/run_all_nopre.sh and models/NED/run_all_nopre.sh with relevant filepaths
  7. ~~Run feats/run_all_nopre.sh and models/NED/run_all_nopre.sh to extract OpenSMILE features for all sound files
  8. Run models/triplet/prep/create_kaldi_files.py to extract Kaldi files
  9. Open feats directory to follow the steps for modelling

Permissions:

ToDo- edit this to reflect the new files Make sure the following directories/files have permissions:

  1. chmod 777 feats
  2. chmod 777 model/NED
  3. chmod 777 feats/emobase2010_haoqi_revised.conf
  4. chmod 777 models/NED/emobase2010_revised.conf ~~3. chmod 755 feats/run_all_nopre.sh ~4. chmod 755 models/NED/run_all_nopre.sh