prosody_features.py

'''
               AAA               lllllll lllllll   iiii                      
              A:::A              l:::::l l:::::l  i::::i                     
             A:::::A             l:::::l l:::::l   iiii                      
            A:::::::A            l:::::l l:::::l                             
           A:::::::::A            l::::l  l::::l iiiiiii     eeeeeeeeeeee    
          A:::::A:::::A           l::::l  l::::l i:::::i   ee::::::::::::ee  
         A:::::A A:::::A          l::::l  l::::l  i::::i  e::::::eeeee:::::ee
        A:::::A   A:::::A         l::::l  l::::l  i::::i e::::::e     e:::::e
       A:::::A     A:::::A        l::::l  l::::l  i::::i e:::::::eeeee::::::e
      A:::::AAAAAAAAA:::::A       l::::l  l::::l  i::::i e:::::::::::::::::e 
     A:::::::::::::::::::::A      l::::l  l::::l  i::::i e::::::eeeeeeeeeee  
    A:::::AAAAAAAAAAAAA:::::A     l::::l  l::::l  i::::i e:::::::e           
   A:::::A             A:::::A   l::::::ll::::::li::::::ie::::::::e          
  A:::::A               A:::::A  l::::::ll::::::li::::::i e::::::::eeeeeeee  
 A:::::A                 A:::::A l::::::ll::::::li::::::i  ee:::::::::::::e  
AAAAAAA                   AAAAAAAlllllllllllllllliiiiiiii    eeeeeeeeeeeeee  

|  ___|       | |                        / _ \ | ___ \_   _|  _ 
| |_ ___  __ _| |_ _   _ _ __ ___  ___  / /_\ \| |_/ / | |   (_)
|  _/ _ \/ _` | __| | | | '__/ _ \/ __| |  _  ||  __/  | |      
| ||  __/ (_| | |_| |_| | | |  __/\__ \ | | | || |    _| |_   _ 
\_| \___|\__,_|\__|\__,_|_|  \___||___/ \_| |_/\_|    \___/  (_)
                                                                
                                                                
  ___            _ _       
 / _ \          | (_)      
/ /_\ \_   _  __| |_  ___  
|  _  | | | |/ _` | |/ _ \ 
| | | | |_| | (_| | | (_) |
\_| |_/\__,_|\__,_|_|\___/ 
                           

This will featurize folders of audio files if the default_audio_features = ['prosody_features']

This uses a voice activity detector to extract out prosody features like pause length and 
other variables.
'''
import argparse, json, os, sys
sys.path.append(os.getcwd()+'/helpers/DigiPsych_Prosody')
from helpers.DigiPsych_Prosody.prosody import Voice_Prosody
import pandas as pd
from datetime import datetime

def prosody_featurize(audiofile,fsize):
    df = pd.DataFrame()
    vp = Voice_Prosody()
    if audiofile.endswith('.wav'):
        print('Prosody featurizing:',audiofile)
        feat_dict = vp.featurize_audio(audiofile,int(fsize))
        features=list(feat_dict.values())[0:-1]
        labels=list(feat_dict)[0:-1]
    
    print(features)
    print(labels)

    return features, labels