Exercise

Spectrograms of heartbeat audio

Spectral engineering is one of the most common techniques in machine learning for time series data. The first step in this process is to calculate a spectrogram of sound. This describes what spectral content (e.g., low and high pitches) are present in the sound over time. In this exercise, you'll calculate a spectrogram of a heartbeat audio file.

We've loaded a single heartbeat sound in the variable audio.

Instructions 1/2

undefined XP

1
2

Import the short-time fourier transform (stft) function from librosa.core.
Calculate the spectral content (using the short-time fourier transform function) of audio.