Music generation (using markov method)
Beyond solving daily logical problems, this project seeks to employ Artificial Intelligence in music composition, attempting to venture into the deeper regions of understanding of both the cognitive AI and the creative human mind. The report describes the design of an automated music composition sys...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2011
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/44291 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-44291 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-442912023-03-03T20:55:27Z Music generation (using markov method) Soh, Poh Kuan. Chan Syin School of Computer Engineering Centre for Multimedia and Network Technology DRNTU::Engineering::Computer science and engineering Beyond solving daily logical problems, this project seeks to employ Artificial Intelligence in music composition, attempting to venture into the deeper regions of understanding of both the cognitive AI and the creative human mind. The report describes the design of an automated music composition system called “Markov Music Generator”, which composes music melodies based on a finite set of existing music phrases designed by a music expert. Using “Markov Chains” as a machine-learning method, the system creates original melodies of the ‘Contemporary Pop’ genre by manipulating the pitch and rhythmic components of music. Modeling after today’s Pop music’s structure, the system is trained by inputs that are classified according to their respective chords. The outputs are then produced by the retrieval of previously trained probabilistic information from Markov’s State Transition Matrices and relevant tables, and generated according to the pre-written chords-sequence, in a successive manner. Within this report, results are presented to show that employing 1st and 2nd Order Markov Chains for the pitch component is able to generate new melodic sequences that are pleasant and diverse, and also able to match the style of the inputs. A separate test setup shows the employing only 1st Order Markov Chains produces better results than using both 1st and 2nd Order ones. Strengths and limitations will also be reviewed. Finally, the report concludes with the discussion of future works that may improve and increase the creativity capacity of the current “Markov Music Generator”. Bachelor of Engineering (Computer Engineering) 2011-06-01T00:47:38Z 2011-06-01T00:47:38Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/44291 en Nanyang Technological University 73 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering |
spellingShingle |
DRNTU::Engineering::Computer science and engineering Soh, Poh Kuan. Music generation (using markov method) |
description |
Beyond solving daily logical problems, this project seeks to employ Artificial Intelligence in music composition, attempting to venture into the deeper regions of understanding of both the cognitive AI and the creative human mind. The report describes the design of an automated music composition system called “Markov Music Generator”, which composes music melodies based on a finite set of existing music phrases designed by a music expert. Using “Markov Chains” as a machine-learning method, the system creates original melodies of the ‘Contemporary Pop’ genre by manipulating the pitch and rhythmic components of music. Modeling after today’s Pop music’s structure, the system is trained by inputs that are classified according to their respective chords. The outputs are then produced by the retrieval of previously trained probabilistic information from Markov’s State Transition Matrices and relevant tables, and generated according to the pre-written chords-sequence, in a successive manner. Within this report, results are presented to show that employing 1st and 2nd Order Markov Chains for the pitch component is able to generate new melodic sequences that are pleasant and diverse, and also able to match the style of the inputs. A separate test setup shows the employing only 1st Order Markov Chains produces better results than using both 1st and 2nd Order ones. Strengths and limitations will also be reviewed. Finally, the report concludes with the discussion of future works that may improve and increase the creativity capacity of the current “Markov Music Generator”. |
author2 |
Chan Syin |
author_facet |
Chan Syin Soh, Poh Kuan. |
format |
Final Year Project |
author |
Soh, Poh Kuan. |
author_sort |
Soh, Poh Kuan. |
title |
Music generation (using markov method) |
title_short |
Music generation (using markov method) |
title_full |
Music generation (using markov method) |
title_fullStr |
Music generation (using markov method) |
title_full_unstemmed |
Music generation (using markov method) |
title_sort |
music generation (using markov method) |
publishDate |
2011 |
url |
http://hdl.handle.net/10356/44291 |
_version_ |
1759853400683446272 |