Python Machine Learning Cookbook - Second Edition

How to do it...

Let's see how to transform audio signals into the frequency domain:

1. Create a new Python file and import the following package (the full code is in the freq_transform.py file that's already provided for you):

import numpy as np 
from scipy.io import wavfile 
import matplotlib.pyplot as plt 

2. Read the input_freq.wav file that is already provided for you:

# Read the input file 
sampling_freq, audio = wavfile.read('input_freq.wav') 

3. Normalize the signal, as follows:

# Normalize the values 
audio = audio / (2.**15) 

4. The audio signal is just a NumPy array. So, you can extract the length using the following code:

# Extract length 
len_audio = len(audio)

5. Let's apply the Fourier transform. The Fourier transform signal is mirrored ...