Computational musicology

Computational musicology is defined as the study of music with computational modeling and simulation. [1] It was started in the 1950s and originally did not use computers, but more of statistical and mathematical methods. Nowadays computational musicology depends largely on complex algorithms . Computer science, computer music, systematic musicology, music information retrieval, computational musicology, digital musicology, sound and music computing and music informatics. [2]


Lejaren Hiller acted as one of the foremost pioneers by creating one of the first musical compositions with a computer in 1957. [3] In the 1960s research continued using statistical and mathematical methods, . 1970s and 1980s were especially significant times for computational musicology as many discoveries were made. Since then the field has suffered a general lack of interest. [4]


Most of the work in computational musicology is done with computers that run specifically designed programs. Commonly they employ the theory and methods of statistical science, mathematics and music theory. Comprehension of the physics of hearing and sound are also required in the analysis of raw audio data.


Music databases

One of the earliest applications in computational musicology was the creation and use of musical databases . Input, utilization and analysis of large amounts of data

Analysis of music

Different computer programs have been developed to analyze musical data. Data formats vary from standard notation to raw audio. Analysis of formats for MIDI , are examples of the most common methods. Significant advances in the analysis of raw data have only recently been made.

Artificial production of music

Different algorithms can be used to create complete compositions and improvise music. One of the methods by which a program of learning improvisation is made of improvisation. Artificial neural networks are used extensively in such applications.

Historical change and music

One developing sociomusicological theory in computational musicology is the “Discursive Hypothesis” proposed by Kristoffer Jensen and David G. Hebert , which suggests that “because both music and language are cultural discourses” (which may reflect social reality in similarly limited be identifiable between the trajectories of significant features of musical sound and linguistic discourse regarding social data. ” [5] According to this perspective, analyzes of ” big data ” can be used to improve understanding of the features of music and society. They are interrelated and change similarly across time. .

Non-western music

Strategies from computational musicology are recently being applied for analysis of music in various parts of the world. For example, professors affiliated with the Birla Institute of Technology in India have produced studies of harmonic and melodic tendencies (in the raga structure) of Hindustani classical music . [7]


RISM’s (International Directory of Musical Sources) database is one of the world’s largest music databases, containing over 700,000 references to musical manuscripts. Anyone can use its search engine to find compositions. [8]

The Center for History and Analysis of Recorded Music (CHARM) has developed the Mazurka Project , [9] which offers “downloadable recordings, analytical software and training materials, and a variety of resources relating to the history of recording.”

See also

  • Music cognition
  • Cognitive musicology
  • Musicology
  • Artificial neural network
  • JFugue


  1. Jump up^ Coutinho, Gimenes, Martins and Miranda (2005): “Computational Musicology: An Artificial Life Approach”, <>
  2. Jump up^ Meredith, David (2016). “Preface”. Computational Music Analysis . New York: Springer. p. v. ISBN  978-3319259291 .
  3. Jump up^ Lejaren Hiller Article Wikipedia,Lejaren Hiller
  4. Jump up^ Wool, Pauli (2005): “Tietokoneavusteisen musiikintutkimuksen menetelmistä” (in Finnish) <>
  5. Jump up^ McCollum, Jonathan and Hebert, David (2014)Lanham, Theory and Method in Historical Ethnomusicology , MD: Lexington Books / Rowman & LittlefieldISBN 0739168266; p.62. Some of Jensen and Hebert’s Pioneering Findings from 2013 on tendencies in USHot Billboard(eg Mauch M, MacCallum RM, Levy M, Leroi AM.) The Evolution of Popular Music: USA 1960 -2010 R. Soc Open Sci., 2: 150081.
  6. Jump up^ Kristoffer Jensen and David G. Hebert (2016). Rating and Prediction of Harmonic Complexity Across 76 Years of Billboard 100 Hits. In R. Kronland-Martinet, M. Aramaki, and S. Ystad, (Eds.), Music, Mind, and Embodiment . Switzerland: Springer Press, pp.283-296. ISBN 978-3-319-46281-3.
  7. Jump up^ Chakraborty, S., Mazzola, G., Tewari, S., Patra, M. (2014)”Computational Musicology in Hindustani Music”New York: Springer.
  8. Jump up^ RISM database, <>
  9. Jump up^ Mazurka Project, <>