Neural network based systems for computer-aided musical composition: supervised x unsupervised learning

Debora Correa; Alexandre L. M Levada; Jose H Saito; Joao F Mari

doi:10.1145/1363686.1364101

Neural network based systems for computer-aided musical composition: supervised x unsupervised learning

Debora Correa, Alexandre L. M Levada, Jose H Saito, Joao F Mari

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Abstract

This ongoing project describes neural network applications for helping musical composition using as inspiration the natural landscape contours. We propose supervised and unsupervised learning approaches, by using Back-Propagation-Through-Time (BPTT) and Self Organizing Maps (SOM) neural networks. In the supervised learning, the network learns certain aspects of musical structure by means of measure examples taken from melodies of the training set and uses these measures learned to compose new melodies using as input the extracted data of the landscapes contour. In the unsupervised learning, the network also uses measure examples as input during training and the extracted data of the landscapes contour in the composition stage. The obtained results show the viability of both approaches.

Original language	English
Title of host publication	SAC '08
Subtitle of host publication	Proceedings of the 2008 ACM symposium on Applied computing
Publisher	Association for Computing Machinery (ACM)
Pages	1738-1742
Number of pages	5
ISBN (Electronic)	978-1-59593-753-7
DOIs	https://doi.org/10.1145/1363686.1364101
Publication status	Published - 16 Mar 2008
Externally published	Yes
Event	The 2008 ACM Symposium on Applied Computing - Fortaleza, Brazil Duration: 16 Mar 2008 → 20 Mar 2008 https://dl.acm.org/doi/proceedings/10.1145/1363686

Conference

Conference	The 2008 ACM Symposium on Applied Computing
Abbreviated title	SAC '08
Country/Territory	Brazil
City	Fortaleza
Period	16/03/08 → 20/03/08
Internet address	https://dl.acm.org/doi/proceedings/10.1145/1363686

Access to Document

10.1145/1363686.1364101

Cite this

@inproceedings{d7a70bde429a4749ab097ff1e7e7957e,

title = "Neural network based systems for computer-aided musical composition: supervised x unsupervised learning",

abstract = "This ongoing project describes neural network applications for helping musical composition using as inspiration the natural landscape contours. We propose supervised and unsupervised learning approaches, by using Back-Propagation-Through-Time (BPTT) and Self Organizing Maps (SOM) neural networks. In the supervised learning, the network learns certain aspects of musical structure by means of measure examples taken from melodies of the training set and uses these measures learned to compose new melodies using as input the extracted data of the landscapes contour. In the unsupervised learning, the network also uses measure examples as input during training and the extracted data of the landscapes contour in the composition stage. The obtained results show the viability of both approaches.",

author = "Debora Correa and Levada, {Alexandre L. M} and Saito, {Jose H} and Mari, {Joao F}",

year = "2008",

month = mar,

day = "16",

doi = "10.1145/1363686.1364101",

language = "English",

pages = "1738--1742",

booktitle = "SAC '08",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "The 2008 ACM Symposium on Applied Computing<br/>, SAC '08 ; Conference date: 16-03-2008 Through 20-03-2008",

url = "https://dl.acm.org/doi/proceedings/10.1145/1363686",

}

Correa, D, Levada, ALM, Saito, JH & Mari, JF 2008, Neural network based systems for computer-aided musical composition: supervised x unsupervised learning. in SAC '08: Proceedings of the 2008 ACM symposium on Applied computing. Association for Computing Machinery (ACM), pp. 1738-1742, The 2008 ACM Symposium on Applied Computing
, Fortaleza, Brazil, 16/03/08. https://doi.org/10.1145/1363686.1364101

Neural network based systems for computer-aided musical composition: supervised x unsupervised learning. / Correa, Debora; Levada, Alexandre L. M; Saito, Jose H et al.
SAC '08: Proceedings of the 2008 ACM symposium on Applied computing. Association for Computing Machinery (ACM), 2008. p. 1738-1742.

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

TY - GEN

T1 - Neural network based systems for computer-aided musical composition

T2 - The 2008 ACM Symposium on Applied Computing<br/>

AU - Correa, Debora

AU - Levada, Alexandre L. M

AU - Saito, Jose H

AU - Mari, Joao F

PY - 2008/3/16

Y1 - 2008/3/16

N2 - This ongoing project describes neural network applications for helping musical composition using as inspiration the natural landscape contours. We propose supervised and unsupervised learning approaches, by using Back-Propagation-Through-Time (BPTT) and Self Organizing Maps (SOM) neural networks. In the supervised learning, the network learns certain aspects of musical structure by means of measure examples taken from melodies of the training set and uses these measures learned to compose new melodies using as input the extracted data of the landscapes contour. In the unsupervised learning, the network also uses measure examples as input during training and the extracted data of the landscapes contour in the composition stage. The obtained results show the viability of both approaches.

AB - This ongoing project describes neural network applications for helping musical composition using as inspiration the natural landscape contours. We propose supervised and unsupervised learning approaches, by using Back-Propagation-Through-Time (BPTT) and Self Organizing Maps (SOM) neural networks. In the supervised learning, the network learns certain aspects of musical structure by means of measure examples taken from melodies of the training set and uses these measures learned to compose new melodies using as input the extracted data of the landscapes contour. In the unsupervised learning, the network also uses measure examples as input during training and the extracted data of the landscapes contour in the composition stage. The obtained results show the viability of both approaches.

U2 - 10.1145/1363686.1364101

DO - 10.1145/1363686.1364101

M3 - Conference paper

SP - 1738

EP - 1742

BT - SAC '08

PB - Association for Computing Machinery (ACM)

Y2 - 16 March 2008 through 20 March 2008

ER -

Neural network based systems for computer-aided musical composition: supervised x unsupervised learning

Abstract

Conference

Access to Document

Fingerprint

Cite this