Evolutionary hypernetworks for learning to generate music from examples

Hyun Woo Kim, Byoung Hee Kim, Byoung Tak Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Evolutionary hypernetworks (EHNs) are recently introduced models for learning higher-order probabilistic relations of data by an evolutionary self-organizing process. We present a method that enables EHNs to learn and generate music from examples. Short-term and long-term sequential patterns can be extracted and combined to generate music with various styles by our method. Based on a music corpus consisting of several genres and artists, an EHN generates genre-specific or artist-dependent music fragments when a fraction of score is given as a cue. Our method shows about 88% of success rate in partial music completion task. By inspecting hyperedges in the trained hypernetworks, we can extract a set of arguments that constitutes melodic structures in music.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Fuzzy Systems - Proceedings
Pages47-52
Number of pages6
DOIs
Publication statusPublished - 2009 Dec 10
Externally publishedYes
Event2009 IEEE International Conference on Fuzzy Systems - Jeju Island, Korea, Republic of
Duration: 2009 Aug 202009 Aug 24

Publication series

NameIEEE International Conference on Fuzzy Systems
ISSN (Print)1098-7584

Conference

Conference2009 IEEE International Conference on Fuzzy Systems
CountryKorea, Republic of
CityJeju Island
Period09/8/2009/8/24

Fingerprint

Music
Sequential Patterns
Self-organizing
Completion
Learning
Fragment
Higher Order
Partial
Dependent

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Kim, H. W., Kim, B. H., & Zhang, B. T. (2009). Evolutionary hypernetworks for learning to generate music from examples. In 2009 IEEE International Conference on Fuzzy Systems - Proceedings (pp. 47-52). [5277047] (IEEE International Conference on Fuzzy Systems). https://doi.org/10.1109/FUZZY.2009.5277047

Evolutionary hypernetworks for learning to generate music from examples. / Kim, Hyun Woo; Kim, Byoung Hee; Zhang, Byoung Tak.

2009 IEEE International Conference on Fuzzy Systems - Proceedings. 2009. p. 47-52 5277047 (IEEE International Conference on Fuzzy Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, HW, Kim, BH & Zhang, BT 2009, Evolutionary hypernetworks for learning to generate music from examples. in 2009 IEEE International Conference on Fuzzy Systems - Proceedings., 5277047, IEEE International Conference on Fuzzy Systems, pp. 47-52, 2009 IEEE International Conference on Fuzzy Systems, Jeju Island, Korea, Republic of, 09/8/20. https://doi.org/10.1109/FUZZY.2009.5277047
Kim HW, Kim BH, Zhang BT. Evolutionary hypernetworks for learning to generate music from examples. In 2009 IEEE International Conference on Fuzzy Systems - Proceedings. 2009. p. 47-52. 5277047. (IEEE International Conference on Fuzzy Systems). https://doi.org/10.1109/FUZZY.2009.5277047
Kim, Hyun Woo ; Kim, Byoung Hee ; Zhang, Byoung Tak. / Evolutionary hypernetworks for learning to generate music from examples. 2009 IEEE International Conference on Fuzzy Systems - Proceedings. 2009. pp. 47-52 (IEEE International Conference on Fuzzy Systems).
@inproceedings{6fcedf7c5eee48768de2915a21af015c,
title = "Evolutionary hypernetworks for learning to generate music from examples",
abstract = "Evolutionary hypernetworks (EHNs) are recently introduced models for learning higher-order probabilistic relations of data by an evolutionary self-organizing process. We present a method that enables EHNs to learn and generate music from examples. Short-term and long-term sequential patterns can be extracted and combined to generate music with various styles by our method. Based on a music corpus consisting of several genres and artists, an EHN generates genre-specific or artist-dependent music fragments when a fraction of score is given as a cue. Our method shows about 88{\%} of success rate in partial music completion task. By inspecting hyperedges in the trained hypernetworks, we can extract a set of arguments that constitutes melodic structures in music.",
author = "Kim, {Hyun Woo} and Kim, {Byoung Hee} and Zhang, {Byoung Tak}",
year = "2009",
month = "12",
day = "10",
doi = "10.1109/FUZZY.2009.5277047",
language = "English",
isbn = "9781424435975",
series = "IEEE International Conference on Fuzzy Systems",
pages = "47--52",
booktitle = "2009 IEEE International Conference on Fuzzy Systems - Proceedings",

}

TY - GEN

T1 - Evolutionary hypernetworks for learning to generate music from examples

AU - Kim, Hyun Woo

AU - Kim, Byoung Hee

AU - Zhang, Byoung Tak

PY - 2009/12/10

Y1 - 2009/12/10

N2 - Evolutionary hypernetworks (EHNs) are recently introduced models for learning higher-order probabilistic relations of data by an evolutionary self-organizing process. We present a method that enables EHNs to learn and generate music from examples. Short-term and long-term sequential patterns can be extracted and combined to generate music with various styles by our method. Based on a music corpus consisting of several genres and artists, an EHN generates genre-specific or artist-dependent music fragments when a fraction of score is given as a cue. Our method shows about 88% of success rate in partial music completion task. By inspecting hyperedges in the trained hypernetworks, we can extract a set of arguments that constitutes melodic structures in music.

AB - Evolutionary hypernetworks (EHNs) are recently introduced models for learning higher-order probabilistic relations of data by an evolutionary self-organizing process. We present a method that enables EHNs to learn and generate music from examples. Short-term and long-term sequential patterns can be extracted and combined to generate music with various styles by our method. Based on a music corpus consisting of several genres and artists, an EHN generates genre-specific or artist-dependent music fragments when a fraction of score is given as a cue. Our method shows about 88% of success rate in partial music completion task. By inspecting hyperedges in the trained hypernetworks, we can extract a set of arguments that constitutes melodic structures in music.

UR - http://www.scopus.com/inward/record.url?scp=71249142334&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71249142334&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2009.5277047

DO - 10.1109/FUZZY.2009.5277047

M3 - Conference contribution

SN - 9781424435975

T3 - IEEE International Conference on Fuzzy Systems

SP - 47

EP - 52

BT - 2009 IEEE International Conference on Fuzzy Systems - Proceedings

ER -