SPEECH AND AUDIO PROCESSING (2/2 Credits)

Learning Outcomes:

On successful completion of this course, student will be able to: LO1 – Explain the fundamental of digital signal processing for audio and speech; LO2 – Apply audio and speech processing based on deep learning method to automatic speech recognition, text to speech, and speaker recognition; LO3 – Build audio and speech processing code in Python programming.

Topics:

1. Final Presentation;
2. Acoustic Feature Extraction using Torchaudio;
3. Keyword Spotting;
4. Keyword Spotting using Deep Learning;
5. Text-to-Speech;
6. Digital Signal Processing;
7. Text-to-Speech using Deep Learning;
8. Acoustic Feature Extraction;
9. Automatic Speech Recognition using Deep Learning;
10. Speaker Recognition using Deep Learning;
11. Introduction to Audio and Audio Library;
12. Audio and Speech Coding;
13. Input/Output using Torchaudio;
14. Automatic Speech Recognition;
15. Audio classification;
16. Audio classification using Torchaudio;
17. Introduction to speech and audio signals;
18. Speaker Recognition;
19. Digital Signal Processing & Spectrogram.