conf.yaml

#---! THIS FILE SHOULD BE MODIFIED BASED ON YOUR CASE

#These variables should be changed
inpath: /media/anwar/D/Data/ASR/Merged_Arabic_Corpus_of_Isolated_Words/original #where input wave data exist
outpath: /media/anwar/E/Voice_Biometrics/SIDEKIT-1.3/py3env/exp/phase02 #where the program outputs exist


#training configuration
#NOTE: the summation of following sessions must be less than or equal 10
enroll_sessions: 3 #number of sessions to be included in the training set
test_sessions: 5   #number of sessions to be included in the test set


#preprocessing configurations
sampling_rate: 44100
bit_precision: 16
no_channels: 1


#features configuration (NOTE: to disable a feature, assign it to None)
features:
  - vad #voice-activity-dectection
  - energy #log-energy
  - cep #cepstral coefficients
  - fb #filter-banks
  #- bnf
cepstral_coefficients: 19
filter_bank: log #filter bank can either be "log" for logarithmic and "lin" for linear
filter_bank_size: 24
lower_frequency: 300
higher_frequency: 3400
vad: snr #can be either "energy", "snr", "percentil" or "lbl".
snr_ratio: 40 #signal-to-noise ratio 
window_size: 0.025 #in seconds (25 milliseconds)
window_shift: 0.010 #in seconds (10 milliseconds)


#UBM configuration
num_gaussians: 64


#i-vectors (tv) configurations (depends on UBM configurations)
batch_size: 30 #size of data batch
tv_rank: 25 # Rank of the total variability matrix
tv_iterations: 50 # number of iterations to train the variability matrix
scoring: cosine #can be either "cosine", or "mahalanobis", or "two_covariance"

#i-vectors (PLDA) configurations (depends on TV configuration)




#plotting configuration
DET_curve: rocch #you can choose either 'rocch' or 'steppy'


#other configuration