Odtnhj

I need to extract features such as duration, meanfreq, sd, median,... from a .wav file (audio sample) to a .csv file.

I have already completed the code but I cant manage to get all features that I need.
The features I would like to have is:

"meanfreq", "sd", "median", "Q25", "Q75", "IQR", "skew", "kurt", "sp.ent", "sfm", "mode", "centroid", "meanfun", "minfun", "maxfun", "meandom", "mindom", "maxdom", "dfrange", "modindx", "label"

The features that I have managed to extract are:

'nobs', 'mean', 'skew', 'kurtosis', 'median', 'mode', 'std', 'low', 'peak', 'q25', 'q75', 'iqr', 'label'

this is my function that I have finished (note: this is only a small part of my code for features, I have more):

def get_features(frequencies): # acoustic attributes
 print("nExtracting features ")
 nobs, minmax, mean, variance, skew, kurtosis = 
 stats.describe(frequencies)
 median = np.median(frequencies)
 mode = stats.mode(frequencies).mode[0]
 std = np.std(frequencies)
 low, peak = minmax
 q75, q25 = np.percentile(frequencies, [75, 25])
 iqr = q75 - q25
 return (nobs, mean, skew, kurtosis, median, mode, std, low, peak, q25, q75, iqr)

I am also aware that there are existing voice.csv datasets on the internet, but I would like the code for converting them from .wav to .csv and be able to extract the features myself rather than to use a preprocessed .csv file.

Thank you so much in advance:)