SGN-9206 Signal processing graduate seminar II, Fall 2009
Music information retrieval

This seminar studies modern techniques for music information retrieval (MIR) and music recommendation. Nowadays, almost all music can be easily and cheaply accessed via the Internet, but at the same time music can be hard to find. This has created the demand for intelligent music retrieval and recommendation services which allow the user to discover artists and songs that he or she likes. MIR research has grown rapidly during the last ten years and some of the developed techniques are already used by millions of people.

This course introduces the various techniques for music retrieval and recommendation, including collaborative filtering, query by example of musical audio, automatic classification of the genre or mood of music, cover song identification, etc (see below for a list of topics).

Course information

Lectured Fall 2009, Periods 1-2

4 credits

Suitable for postgraduate studies

Instructor: Anssi Klapuri

Literature: selected articles based on which the presentations are prepared


Exam is arranged on Tuesday 24.11. at 14:15 o'clock in TB222 (normal time and place). The exam questions are based on the presentation slides: if you have attended the seminar presentations, you do not need to study the source articles, but reading the presentation slides is enough. The exam is graded pass/fail.

Lecture time and place

Periods 1-2: Tuesday 14-16, TB222

Scheduled presentations and slides of presentations (forgot your password? e-mail anssi.klapuri at

Seminar attendance. -->

Practical implementation

The first 2 x 45 minute lectures are given by the instructor. The rest of the seminar consists of student presentations.

Each individual student prepares a 45-minute presentation on a topic chosen together by the instructor and the student.

Course plan:

Requirements for passing the course

This seminar in previous years

Page created in August 2009 by Anssi Klapuri, klap @ cs tut fi