Unit 1. Working with audio data

What you’ll learn in this unit

Every audio or speech task starts with an audio file. Before we can dive into solving these tasks, it’s important to understand what these files actually contain, and how to work with them.

In this unit, you will gain an understanding of the fundamental terminology related to audio data, including waveform, sampling rate, and spectrogram. You will also learn how to work with audio datasets, including loading and preprocessing audio data, and how to stream large datasets efficiently.

By the end of this unit, you will have a strong grasp of the essential audio data terminology and will be equipped with the skills necessary to work with audio datasets for various applications. The knowledge you’ll gain in this unit is going to lay a foundation to understanding the remainder of the course.