Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Machine Learning and Big Data Processing with Audio and MusicModule description #11005 / Version 1

← Module page Deutsche Fassung
Module / Version#11005 / #1
ValiditySince Summer semester 2025
Available language(s)English, German
Credit points6
Person responsible for the moduleLepa, Steffen
GradingGraded
Exam formatHomework
Language(s) of instructionEnglish, German

Affiliation

FacultyFakultät I
InstituteInstitut für Sprache und Kommunikation
Academic chair31351200 FG Audiokommunikation (Audio Communication)

Contact

OfficeEN 8
Contact personWeinzierl, Stefan
E-mail addressstefan.weinzierl@tu-berlin.de
Websitehttps://www.tu.berlin/ak

Learning outcomes

On successful completion of the module, students will be able to
- use Python and/or R libraries relevant to audio, music information retrieval, music metadata retrieval, and machine learning (such as numpy, sklearn, torch, pandas, etc.);
- understand machine learning theory and apply machine learning methods in practice;
- analyse audio, music, lyrics and music metadata using statistical and machine learning methods;
- implement audio and music ML applications;
- set up and optimise machine learning workflows, pipelines and lifecycles;
- understand and implement research in audio and music using machine learning;
- evaluate the success and validity of machine learning models using relevant objective metrics and subjective tests;
- learn how to interpret and communicate machine learning results in science as well as for laypeople;
- critically examine the impact of data acquisition and machine learning on artists, musicians, listeners, cultural scenes, the environment and society.

Content

- API-based music data retrieval and webscraping
- Interpretable Machine Learning and Deep Learning fundamentals
- Machine Learning Frameworks and Architectures
- Preprocessing for Audio and Music Data (Data Augmentation, Missing Value Imputation, Stratification)
- Theory of Random Forests and Neural Networks
- Hyperparameter Tuning and Training Procedures for Audio and Music Data
- Optimisation Methods and Best Practices for Audio and Music ML
- Quality and validity evaluation of ML Models

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Big Data Processing with Audio and MusicLecture Winter semester[de]2 ISIS
Machine Learning for Audio DataIntegrated course Winter semester[en]2 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (2)

Big Data Processing with Audio and Music (Lecture) 1

All groups of this course in the catalog

Machine Learning for Audio Data (Integrated course) 1

All groups of this course in the catalog

Workload and credit points

Big Data Processing with Audio and Music (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing152 h30 h
60 h

Machine Learning for Audio Data (Integrated course)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing152 h30 h
60 h

Course-independent workload

Workload descriptionMultiplierHoursTotal
Project work140 h40 h
Preparation written test120 h20 h
60 h

The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.

Description of teaching and learning methods

Lecture, integrated course, for more detailed descriptions see AllgStuPO §47 Types of course

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

This module has no desirable prerequisites for the courses.

Mandatory requirements for the module examination registration:

The examination requirements could not be retrieved.

Completion of the module

GradingGraded
Exam formatHomework
LanguageEnglish, German
Duration/Extent8-10 pages plus code

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Winter semester.

Maximum number of participants

The maximum capacity of participants is 30.

Registration procedures

Registration for the module examination is done via the electronic registration system of the TU Berlin.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

unavailable

Recommended literature

No recommended literature given

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Audio Communication and Technology
Audio Communication and Technology (M. Sc.) - StuPO 2014
SS 2025Wahlpflichtmodule › Vertiefung
WS 2025/26Wahlpflichtbereich Vertiefung
SS 2026Wahlpflichtbereich Vertiefung
WS 2026/27Wahlpflichtbereich Vertiefung
Audio Communication and Technology
Audio Communication and Technology (M. Sc.) - StuPO 2024
WS 2025/26Wahlpflichtbereich › Wahlpflichtbereich Vertiefung
SS 2026Wahlpflichtbereich › Wahlpflichtbereich Vertiefung
WS 2026/27Wahlpflichtbereich › Wahlpflichtbereich Vertiefung

Miscellaneous

Not specified