1. Learn
    2. /
  2. Courses
    3. /
  3. Machine Learning for Time Series Data in Python

Exercise

Calculating the envelope of sound

One of the ways you can improve the features available to your model is to remove some of the noise present in the data. In audio data, a common way to do this is to smooth the data and then rectify it so that the total amount of sound energy over time is more distinguishable. You'll do this in the current exercise.

A heartbeat file is available in the variable audio.

Instructions 1/3

undefined XP
    1
    2
    3

Visualize the raw audio you'll use to calculate the envelope.