Audio features

[EmreOzkose]

Hi,

Can you share a script to extract features of raw inputs? I am trying to extract audio features with open-smile. When I extract eGeMAPS features, I got 88-dimensional array, however paper says audio features are 154-dimensional

import os
import opensmile
import audiofile

smile = opensmile.Smile(
    feature_set=opensmile.FeatureSet.eGeMAPSv02,
    feature_level=opensmile.FeatureLevel.Functionals,
)
len(smile.feature_names) # 88

signal, sampling_rate = audiofile.read(
    "path/to/wav",
    duration=30,
    always_2d=True,
)

smile.win_dur = 25
smile.hop_dur = 10

feature = smile.process_signal(
    signal,
    sampling_rate
)
# feature dimension is 88