List of courses related to Music Information Retrieval


MIR-related courses worldwide!



Teacher
Course name (link)
Program
Institution
Country
Course description
Level
Language
Keywords
Stephan Baumann
Music Recommendation Systems
Bachelor of the Arts
Bachelor of Science
Popakademie Baden-Württemberg, Technical University Kaiserslautern
Germany
Music recommendation algorithms: Concepts, Examples, Applications, Commercial players, Theory of Content-based, Collaborative Filtering and Hybrid Approaches including vector space model, similarity metrics, basics of MIR features, metadata, user models. Extensions to social and semantic processing.
Under-graduate

music recommender, content-based, CF, hybrid, social, semantic, echonest, bmat, itunes, metadata, user model, cosine metric, hypemachine, RDF
Alexander Lerch
Computational Music Analysis
MSc in Music Technology
Georgia Tech Center for Music Technology
USA
Lectures: presentation of digital audio signal processing methods for the analysis and automatic extraction of (musical) content from audio signals.

Seminar: Implementation of a project work in Matlab.

Course material (slides, github, etc.)
Graduate
English
audio content analysis, music information retrieval, machine listening, computational auditory scene analysis, digital signal processing, music informatics,
feature extraction, music classification, tempo detection, key detection, pitch tracking, mood recognition, fingerprinting, music performance analysis
Fabien Gouyon
Music Information Retrieval
Master in Multimedia
Faculty of Engineering, University of Porto
Portugal

Graduate
English

Simon Dixon
Music Analysis and Synthesis
MSc Digital Music Processing
Queen Mary University of London
UK
This course introduces students to common methods for the analysis and synthesis of digital audio. It presents in-depth studies of general approaches to the low-level analysis of audio signals, and follows these with specialised methods for the semantic analysis of music signals, including the extraction of information related to the rhythm, melody, harmony and instrumentation of recorded music. This is followed by an examination of the most important methods of sound synthesis, including wavetable, sampling, additive, subtractive, modulation, and physical modelling synthesis.
Graduate
English
Music signal processing, audio DSP, phase vocoder, sinusoidal modelling, transient detection, onset detection, tempo induction, beat tracking, polyphonic transcription, instrument identification, source separation, wavetable synthesis, sampling synthesis, additive synthesis, subtractive synthesis, FM synthesis, physical modelling synthesis
Markus Schedl
Music Information Retrieval
Computer Science
Johannes Kepler University Linz
Austria
This lecture gives an introduction to techniques and applications used in Music Information Retrieval. The main topics covered are feature extraction (content- and context-based features), similarity measurement, applications of MIR, data projection and visualization, and user interfaces.
Under-graduate


Jan Larsen
02452 Audio Information Processing Systems
Master of Science in Mathematical Modelling and Computation
Technical University of Denmark
Denmark
The aim of this course is to enable students to understand, implement, and analyze systems that create, modify, or extract information from audio data.

The course wil start spring 2013 and run in sping semesters. Webpage will be accessible late November 2012.
Graduate

machine learning models, MIR, audio signal processing, content analysis, segmentation, source separation, source ehancement
Juan Pablo Bello
Music Information Retrieval
Music Technology
New York University
USA
This course gives a comprehensive overview of research on the multi-disciplinary field of Music Information Retrieval (MIR). MIR uses knowledge from areas as diverse as signal processing, machine learning, information and music theory. The course will explore how this knowledge can be used for the development of novel methodologies for browsing and retrieval on large music collections, a hot topic given recent advances in online music distribution and searching. Emphasis would be given to audio signal processing techniques.
Graduate
English
music information retrieval, music informatics, audio content analysis, signal processing, machine listening, computer audition
Emilia Gómez
Music Information Retrieval
Master in Sound and Music Computing
Universitat Pompeu Fabra
Spain
This course provides a survey of the field of Music Information Retrieval (MIR), paying attention to recent developments and applications. A special emphasis is given to techniques for the automatic description of music content in terms of different facets (e.g. melody, harmony, rhythm, timbre), temporal scopes and abstraction levels (from low-level features to semantic descriptions such as genre or mood). In addition, we review methods for music description from contextual data sources such as web pages or social networks. The combination of music content and context description enables a wide variety of music retrieval tasks, that are adapted to user needs and evaluated according to some defined methodologies.
Graduate
English
audio content description, melody, timbre, rhythm, music similarity, classification, context description.

Intelligent Audio Systems: Foundations and Applications of Music Information Retrieval (MIR)
CCRMA Summer Workshop
(Center for Computer Research in Music and Acoustics)
Stanford University
USA
This workshop is intended for: students, researchers, and industry audio engineers who are unfamiliar with the field of Music Information Retrieval (MIR). Lectures will cover topics such as low-level feature extraction, generation of higher-level features such as chord estimations, audio similarity clustering, search, and retrieval techniques, and design and evaluation of machine classification systems. Our goal is to make the understanding and application of highly-interdisciplinary technologies and complex algorithms approachable.
Graduate
English
music information retrieval, machine learning for audio, audio signal processing
Dan Ellis
Music Signal Processing
Electrical Engineering
Columbia University
USA
A survey of applications of signal processing to music audio applications from analog synthesis through to cover song matching. Many practicals based on Pd and Matlab; all materials available online.
Graduate
English
music, audio, signal processing, matlab, puredata
Meinard Müller
Music Processing
Master in Engineering
University of Erlangen-Nuremberg
Germany
Music signals possess specific acoustic and structural characteristics that are not shared by spoken language or audio signals from other domains. In fact, many music analysis tasks only become feasible by exploiting suitable music-specific assumptions. In this course, we study feature design principles that have been applied to music signals to account for the music-specific aspects. In particular, we discuss various musically expressive feature representations that refer to musical dimensions such as harmony, rhythm, timbre, or melody. Furthermore, we highlight the practical and musical relevance of these feature representations in the context of current music analysis and retrieval tasks. Here, our general goal is to show how the development of music-specific signal processing techniques is of fundamental importance for tackling otherwise infeasible music analysis problems.
Graduate
English
music information retrieval, audio, signal processing
Bryan Pardo
Machine Perception of Music
EECS
Northwestern University
USA
Machine Perception of Music will introduce students to the field of computational music perception through a combination of lectures, readings, and lab work in MATLAB. Students will learn basics of how sound and music are recorded and encoded by computers as .wav and MIDI files. The class will also explore basics of audio perception, including the relationship between pitch and frequency and the difficulties inherent in auditory scene analysis by humans and machines. Basic classification and sequence alignment techniques will also be introduced.
Under-graduate
English
audio,music perception, MIR, information, retrieval
Perfecto Herrera
Tecnologies per a la recerca musical (Technologies for Music Research)
B.A. Music (Musicology / Sonology)
Escola Superior de Música de Catalunya (ESMUC)
Spain
Introduction to computational literacy, empirical research on musicological and sonological problems, procedural thinking, computational principles, techniques and tools to tackle music research problems.
Under-graduate
Catalan
Computational literacy, digitization, audio analysis, score analysis, text analysis, statistics and data mining
Michael Casey
Music, Information, Neuroscience
Graduate Program, Digital Musics
Dartmouth College
USA
This course covers theory and practice of music audio information systems with an emphasis on creative and emerging applications. Topics include information theory, audio feature extraction methods, metric spaces, similarity methods, mathematical and computational models of music, probability and statistics of music feature spaces, machine learning and decision support systems, links between surface-levels and deep structure in music, comparative analysis of music collections, audio and multimedia search engines, creative systems, scalability to large audio collections, and modeling of human music cognition using EEG and fMRI data.
Graduate
English
music informatics, computational neuroscience, MVPA, fMRI, Python
Michael Scott Cuthbert
Quantitative Approaches to Music History
21m.269,
OpenCourseWare
Music (B.Science)
MIT
USA
This course presents the major approaches, results, and challenges of computational musicology through readings in the field, gaining familiarity with datasets, and hands-on workshops and assignments on data analysis and "corpus" (i.e., repertory) studies. Approximately every other class session will be a discussion/lecture, with alternating classes being labs in using digital tools for studying music. The class culminates in an independent research project in quantitative or computational musicology that will be presented to the class as a whole.
Under-graduate
English
musicology, symbolic MIR, music theory
Isabel Barbancho
Cryptography, Security,and Content Analysis
Máster en Tecnologías de Telecomunicación
Universidad de Málaga
Spain
Intelligent methods are needed for the creation and management of musical information, so that musical contents are accessible, interactive and reusable over time. It is necessary to join contents, knowledge and learning so that information can be produced, stored, managed, personalized, transmitted, preserved and used reliably and efficiently for everyone. Therefore, it is crucial to provide computer systems with the ability to interpret and analyze the musical contents so that access to information is easy and intuitive.
Graduate


Ichiro Fujinaga
Music Information Acquisition, Preservation, and Retrieval
Music Technology
McGill University
Canada
This seminar will investigate the current research activities in the area of music information retrieval. The goal is discovering ways to efficiently find and retrieve musical information. Although the field is relatively new, it encompasses various music disciplines including music analysis, music education, music history, music theory, music psychology, and audio signal processing.

Each student will be expected to present various music information retrieval topics along with literature reviews. Each presentation should be accompanied by web pages created by the presenter. Final project may consist of software development, a theoretical paper, or an extended review paper. Class format will be presentations followed by discussions.

Potential topics include: Themefinder, MELDEX, Cantus, audio content analysis and search, web crawling, melodic similarities, computer-aided transcription, beat tracking, timbre recognition, speech / music separation, P2P technologies, audio and music formats (MPEG-4/7/21, MP3, MusicXML), and Web Services.
Graduate
English
Classifiers, standards, representations, recognition, analysis, transcription, annotations, similarity, usability, web services, evaluation
Jin Ha Lee
User Studies in Music Information Retrieval
Information Science
Information School, University of Washington
USA
This course is designed for those who are interested in exploring user aspects of music information retrieval (MIR) research, including examining the methods used in contemporary research and designing an MIR user study. In this graduate seminar, students will read and discuss a broad sample of user studies from the MIR literature and relevant papers discussing qualitative and quantitative research methods. Over the course of the quarter, each student will design and pilot a user study for investigating an aspect of music information behavior.
Graduate
English
User study, User behavior, User needs, Usability, Evaluation
Anja Volk
Sound and music technology
Game and Media Technology
Department of Information and Computing Sciences, Utrecht University
The Netherlands
This course has been designed for master students in game and media technology. Students learn
how to apply and develop computational methods to extract, process and utilize music information from digital sound and music. They learn both basic concepts on how human listeners extract, make sense of and give meaning to information from sound and music, and how these basic concepts are used, researched and applied through computational technology.
Graduate
English
algorithms, interaction, music information retrieval, game music, music generation, automatic music analysis
Jean Julien Aucouturier
Audio pattern recognition
New Media
Université de Franche-Comté
France
A short (16-hrs) hands-on course on audio pattern recognition, taking students with no technical knowledge (no programming, basic maths) through the building of their own pattern recognition algorithm with Octave/Matlab. 1) how to manipulate sound with Octave (spectrograms and whatnot) 2) building classifiers with 2 features (spectral centroid + spectral flatness) and single gaussian model, 3) building GMMs of MFCCs. I enjoy teaching this class because it is both very basic, and still a gateway for me to provide explanations as complex as needed (curse of dimensionality, generative vs discriminative models, etc.)
Under-graduate
French
pattern recognition, audio, music, non-technical
Alexander Schindler, Andreas Rauber
Information Retrieval
MSc in Computer Science
Vienna University of Technology
Austria
Principles of IR Application domains and associated Feature Spaces, Information Extraction, Retrieval Methods, Relevance Feedback Classification Methods.
The course includes two lectures and a lab example on Music Information Retrieval.
The different aspects of information retrieval are tought by a group of researchers, each giving insights into their research domains.
Music Information retrieval is coverd by Andreas Rauber and Alexander Schindler.
Graduate

Information Retrieval, Music Information Retrieval, Text Retrieval
Eleanor Selfridge-Field, Craig Stuart Sapp
Introduction to Musical Information;
Music Query, Analysis, and Style Simulation
Multiple: M.S./Ph.D. in Music, Science, Technology; M.S./Ph.D. in Computer Science
Stanford University
USA
Introduction of Musical Information (Music 253/CS275A) lays the foundations for music information retrieval by examining and comparing the structure and content of many music formats (for sound, notation, and analysis).
Using an open-source analysis platform (such as the Humdrum Toolkit and various supplements, students plan and design their own applications or enhance applications of other kinds.
Class time is divided during the first four weeks to cover basic areas of music analysis (melodic comparison, rhythmic articulation, principles of harmony) and retrieval and to learn some of the basic principles of the Humdrum Toolkit. Data is available at the KernScores website, MuseData, and Josquin Research Project websites.
Graduate
English
symbolic data, analysis, data translation, visualization, music query, Humdrum, KernScores, MuseData, Josquin Research Project
Zhiyao Duan
Computer Audition
Electrical and Computer Engineering
University of Rochester
USA
This course is a graduate course covering current research in the field. The class starts with a brief review of signal processing techniques, then introduces auditory models, audio features, and audio modeling methods. More advances in state-of-the-art research topics including multi-pitch analysis, source separation, source localization, instrument identification then follow.
Graduate
English
computer audition, music information retrieval, machine learning, signal processing, music transcription, source separation
Yi-Hsuan Yang and Li Su
Music Information Retrieval
Computer Science
National Tsing Hua University
Taiwan
This course covers the signal processing and machine learning techniques relevant to music information retrieval.
Graduate
English
Music information retrieval, automatic music transcription, source separation, cross cultural MIR
Kyogu Lee
Music Information Retrieval Systems
Program in Digital Contents and Information Studies
Seoul National University
Korea
"How do I search for or discover music?"
"I'd like to extract or remove only the vocal from the recorded music. Can I do it?"
"I don't need songs in the top 10 list because they're all sound the same. Please recommend me something else I would really like!"

Music Information Retrieval Systems will consist of a series of lectures and labs that describe and implement the Music Information Retrieval (MIR) systems that try to answer the above-mentioned questions. Basic knowledge in audio signal processing and familiarity with Matlab are preferred but not required. This course intends to attract any undergrad or grad students who love music and are interested in a new and fascinating field of MIR. In the final project, each student is encouraged to select the topic of his/her own and build a simple, but real-working MIR system.
undergrad/graduate
Korean/English
music retrieval, music search/discovery, music content analysis, digital audio signal processing, machine learning
Alexander Refsum Jensenius
Sound Analysis
Musicology
University of Olso
Norway
Covering sound, sound perception and machine-based sound analysis, with practical work in Max, PD and Matlab.
Graduate
English/Norwegian


J.-S. Roger Jang
Music Signal Analysis and Retrieval
Computer Science and Information Engineering
National Taiwan University
Taiwan
The course is aimed to provide students with necessary theoretical background and programming techniques for music signal analysis and music information retrieval. For the analysis part, we shall focus on feature extraction over audio music, including pitch tracking, onset detection, beat tracking, etc. For the retrieval part, we shall cover machine learning methods for various tasks such as query by singing/humming, audio fingerprinting, genre classification, mood classification, cover song identification, singing scoring, score following, etc. The students are also expected to collect corpora to be used in programming contests in the class. MATLAB will be used extensively in our working examples, homework, and programming contests.
Graduate
English
Music signal analysis, music information retrieval, query by singing/humming, audio fingerprinting, music mood/genre classification, cover song identification.

Yi-Hsuan Yang and Li Su
Music Information Retrieval
Computer Science
National Tsing Hua University
Taiwan
This course covers the signal processing and machine learning techniques relevant to music information retrieval.
Graduate
English
Music information retrieval, automatic music transcription, source separation, cross cultural MIR

Roger B. Dannenberg
Computer Music Systems and Information Retrieval
Emerging Media Master (EM2), Sound and Music Computing area
Carnegie Mellon University
USA
This course covers a number of topics related to computer music systems: representation, real-time control, automatic music listening and generation. An overview of machine learning and a project on genre classification is included.
Graduate
English
music listening, music understanding, classification, interactio


If you would like to contribute to this page, please fill this questionnaire or edit this page.