Artificial Intelligence for Music
A.Y. 2025/2026
Learning objectives
The aim of the course is to introduce students to the musical applications of machine learning, considering both aspects of analysis and content generation by means of artificial intelligence. Special attention will be given to audio feature extraction, basic machine learning systems, and the most relevant practices related to computational creativity and generative systems for sound and music.
Expected learning outcomes
The student will acquire basic skills for the analysis, classification and clustering of musical audio signals, as well as knowledge of the historical and phenomenological aspects of generative practices of musical content, and the ability to design simple generative systems.
Lesson period: Second semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
Second semester
Course syllabus
Part 1: Music Analysis and Classification
1. MATLAB exercises
2. Arrays, sound and melodies in Matlab
3. Spectrogram and melody generation
4. Audio denoising
5. Evaluation of audio denoising on music genres
6. Visualization of Chromogram of different music genres
7. Classification of musical instruments
8. Music genre classification
9. Clustering of musical instruments
10. Decision Tree for Artist Classification
11. Comparison of kNN vs. DT for Music emotion recognition
12. DT for music genre classification
Part 2: Automatic generation
- History of generative arts
- Computational creativity
- Tools (computer, mathematical and statistical) for the development of generative multimedia systems
- Basics of interactive systems and sound design
- Sonification and data-driven musical forms
1. MATLAB exercises
2. Arrays, sound and melodies in Matlab
3. Spectrogram and melody generation
4. Audio denoising
5. Evaluation of audio denoising on music genres
6. Visualization of Chromogram of different music genres
7. Classification of musical instruments
8. Music genre classification
9. Clustering of musical instruments
10. Decision Tree for Artist Classification
11. Comparison of kNN vs. DT for Music emotion recognition
12. DT for music genre classification
Part 2: Automatic generation
- History of generative arts
- Computational creativity
- Tools (computer, mathematical and statistical) for the development of generative multimedia systems
- Basics of interactive systems and sound design
- Sonification and data-driven musical forms
Prerequisites for admission
It is recommended that you have passed the signal processing exam.
Teaching methods
Oral presentations and practical lessons.
Teaching Resources
Introduction to Audio Analysis A MATLAB Approach
Assessment methods and Criteria
For the first part of the program: project development
For the second part of the program: an oral exam.
The evaluation is expressed in thirtieths.
For the second part of the program: an oral exam.
The evaluation is expressed in thirtieths.
Professor(s)