Audio Pattern Recognition

A.Y. 2025/2026
6
Max ECTS
48
Overall hours
SSD
INF/01
Language
English
Learning objectives
The course aims at introducing the students to fundamental concepts of data mining algorithms and how these are adapted for needs of audio signal processing and recognition. The principal
statistical modeling techniques are presented inluding neural networks and hidden Markov models.
Expected learning outcomes
The student is expected to understand the operation of the princical data mining algorithms. The student will gain the ability to design and implement the entire pipeline of an audio pattern
recognition system.
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
First four month period
Course syllabus
Data mining
-statistics
-clustering algorithms (partitional and hierarchical)
-traditional machine learning for classification
-model-based anomaly detection

Audio analysis
-signal transformations
-filtering
-feature extraction
-pattern recognition
-alignment and temporal modeling
-music information retrieval
-audio self supervised learning
Prerequisites for admission
It is suggested that the student is familiar with the content of digital signal processing and statistics.
Teaching methods
Oral presentations and practice lessons
Teaching Resources
Books
1. Introduction to Data Mining (Second Edition), https://www-users.cse.umn.edu/~kumar001/dmbook/index.php

2. Data Mining Practical Machine Learning Tools and Techniques (weka book) https://tjzhifei.github.io/links/DM3.pdf

3. Introduction to Audio Analysis, https://www.sciencedirect.com/book/9780080993881/introduction-to-audio-analysis
Assessment methods and Criteria
Project development and oral examination. The evaluation is expressed in thirtieths.
INF/01 - INFORMATICS - University credits: 6
Lessons: 48 hours