DT2470 Music Informatics 7.5 credits


Music is everywhere, but how might it be made as searchable as text? This course digs into the details of extracting information from music data. Such technology can be used to search and retrieve music (like Shazam), recommend music and create playlists (like Spotify), and identifying musical instruments, rhythm, chords, and so on. Come see how signal processing can combine with machine learning to create useful and fun applications.

Show course information based on the chosen semester and course offering:

Offering and execution

No offering selected

Select the semester and course offering above to get information from the correct course syllabus and course offering.

Course information

Content and learning outcomes

Course contents *

Overview of music informatics, its history and applications as well as a review of basic principles, such as music representation, analog to digital conversion and Fourier transform.
Feature extraction that shows how music data can be described in different domains e g time, frequency and time-frequency.
How music content at different levels of abstraction can be expressed and compared with distinctive features.
Ways to model music data by means of statistical machine learning methods.
Evaluation of models of music data and their application in reality.

Intended learning outcomes *

After passing the course, the student should be able to
• explain how music can be represented in reality and in the computer,
• account for how feature extraction works and explain why it is needed,
• summarise and explain which distinctive features that can be extracted from a music signal, based on time, frequency and time-frequency,
• use existing software libraries for feature extraction and interpret distinctive features that have been extracted from a music signal,
• recommend methods for comparing and modelling of music data,
• design and implement own methods for modelling of music data,
• evaluate a given method for modelling of music data and explain its limitations, in order to
• be able to describe how information on different abstraction levels can be extracted from music data (acoustic as well as symbolic) and be used in many applications (e g search, retrieval, synthesis),
• be able to design algorithms for handling and modelling of music data as well as evaluate their performance,
• be able to appreciate the latest technology in music informatics and build on it.

Course Disposition

No information inserted

Literature and preparations

Specific prerequisites *

• Completed course DT1130 Spectral transforms 7.5 credits or EQ1220 Signal theory 7.5 credits or equivalent course.
• Completed course DD2421 Machine learning 7.5 credits or EQ1220 Signal theory 7.5 credits or equivalent course.

Recommended prerequisites

No information inserted


Computer room or own computer.


Information about the course literature will be announced in the course memo.

Examination and completion

If the course is discontinued, students may request to be examined during the following two academic years.

Grading scale *

A, B, C, D, E, FX, F

Examination *

  • LAB1 - Laboratory work, 3.0 credits, Grading scale: P, F
  • PRO1 - Project, 3.0 credits, Grading scale: A, B, C, D, E, FX, F
  • UPP1 - Written report, 1.5 credits, Grading scale: A, B, C, D, E, FX, F

Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.

The examiner may apply another examination format when re-examining individual students.

The examiner decides, in consultation with KTH's coordinator for disabilities (Funka), about possible adapted examination for students with documented, permanent disabilities. The examiner may permit other examination format for re-examination of individual students.

Opportunity to complete the requirements via supplementary examination

No information inserted

Opportunity to raise an approved grade via renewed examination

No information inserted


Sten Ternström

Ethical approach *

  • All members of a group are responsible for the group's work.
  • In any assessment, every student shall honestly disclose any help received and sources used.
  • In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.

Further information

Course web

Further information about the course can be found on the Course web at the link below. Information on the Course web will later be moved to this site.

Course web DT2470

Offered by

EECS/Intelligent Systems

Main field of study *

Computer Science and Engineering

Education cycle *

Second cycle

Add-on studies

No information inserted

Supplementary information

In this course, the EECS code of honor applies, see: