AudioSignalProcessingForML

Code and slides of my YouTube series called "Audio Signal Proessing for Machine Learning"

This repository is a comprehensive collection of resources, code, and explanations for understanding and implementing audio signal processing techniques, with a focus on applications in machine learning. It serves as a learning guide, starting from the fundamentals of sound and waveforms and progressing to advanced feature extraction methods.

Note on Versioning

While this v2 release is fully functional and optimized for current environments, it may differ from the original version shown in the course. The codebase has been updated to reflect modern best practices and improved dependency management. Consequently, the original course version has been deprecated; however, it remains available in the legacy branch for those wishing to follow the video content exactly.

Course Structure

Foundational Concepts

1. Overview: Video | Slides
2. Sound and waveforms: Video | Slides
3. Intensity, loudness, and timbre: Video | Slides | Notebook
4. Understanding audio signals: Video | Slides

---

Feature Extraction Theory

5. Types of audio features for ML: Video | Slides
6. How to extract audio features: Video | Slides
7. Time-domain audio features: Video | Slides

---

Time-Domain Implementation

8. Implementing the amplitude envelope: Video | Notebook
9. RMS energy and zero-crossing rate: Video | Notebook

---

Frequency-Domain Concepts

10. Fourier Transform: The Intuition: Video | Slides
11. Complex numbers for audio signal processing: Video | Slides
12. Defining the Fourier transform using complex numbers: Video | Slides | Notebook
13. Discrete Fourier Transform: Video | Slides

---

Frequency-Domain Implementation

14. Extracting the Discrete Fourier Transform: Video | Notebook
15. Short-Time Fourier Transform explained easily: Video | Slides
16. Extracting Spectrograms from Audio with Python: Video | Notebook
17. Mel Spectrogram Explained Easily: Video | Slides
18. Extracting Mel Spectrograms with Python: Video | Notebook
19. MFCCs Explained Easily: Video | Slides
20. Extracting MFCCs with Python: Video | Notebook
21. Frequency-Domain Audio Features: Video | Slides
22. Implementing Band Energy Ratio from Scratch with Python: Video | Notebook
23. Spectral centroid and bandwidth: Video | Notebook

---

Audio examples

• audio_resources/: A collection of .wav files used for the examples in the notebooks.