Uploaded January 2022 | Updated September 2026, 2 weeks ago

---

Learn audio augmentation techniques both in the raw audio and spectrogram domains.

Specifically, you’ll learn about:
📌 Time shifting
📌 Time stretching
📌 Pitch scaling
📌 Noise addition
📌 Impulse response addition
📌 Filters
📌 Polarity Inversion
📌 Random gain
📌Time masking
📌 Frequency masking

Slides:
github.com/musikalkemist/audioDataAugmentationTutorial/blob/main/2/Audio%20Data%20Augmentation%20Techniques.pdf

=========================

Interested in hiring me as a consultant?
valeriovelardo.com

Join The Sound Of AI Slack community:
valeriovelardo.com/the-sound-of-ai-community

Connect with Valerio on Linkedin:
linkedin.com/in/valeriovelardo

Follow Valerio on Facebook:
facebook.com/TheSoundOfAI

Follow Valerio on Twitter:
twitter.com/musikalkemist

=========================

0:00 Intro
0:19 Raw audio vs spectrogram augmentation
1:06 Time shifting
1:36 Time stretching
2:12 Pitch scaling
3:04 Noise addition
3:44 Impulse response addition
4:42 Filters
5:21 Polarity Inversion
5:53 Random gain
7:21 SpecAugment
8:27 Time masking
9:37 Frequency masking
10:55 Other spectrogram augmentation techniques
12:07 Join The Sound of AI community!
12:40 Coming up