• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Computer Music Generation via Deep Neural Networks

Student: Pilipchuk Serafim

Supervisor: Ilya Makarov

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2020

Music is art of sounds that reflects the reality and influences on humans by musical images, and it is not just a set of tones, their intensities and durations. Conversely, it is a set of complex harmonic relations between each note, a melody line and the idea of the author which altogether forms musical and philosophical sense. The problem of machine understanding of musical sense can be solved by using a mathematical implementation of generally known harmonic rules which musicians use to define the musical idea and recurrent neural networks. The main goal of this paper is to develop an algorithm based on long short-term memory neural network that generates music and computes the quality function by applying mathematically presented musical rules of harmonica and analyze results of this algorithm and results of existing methods of music generation.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses