dc.date.accessioned | 2020-07-02T18:09:49Z | |
dc.date.available | 2020-07-02T18:09:49Z | |
dc.date.created | 2019-10-10T17:06:25Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Weber, Aline Alegre, Lucas N. Tørresen, Jim Castro da Silva, Bruno . Parameterized Melody Generation with Autoencoders and Temporally-Consistent Noise. Music Proceedings of the International Conference on New Interfaces for Musical Expression. 2019, 174-179. Porto Alegre: Universidade Federal do Rio Grande do Sul | |
dc.identifier.uri | http://hdl.handle.net/10852/77398 | |
dc.description.abstract | We introduce a machine learning technique to autonomously generate novel melodies that are variations of an arbitrary base melody. These are produced by a neural network that ensures that (with high probability) the melodic and rhythmic structure of the new melody is consistent with a given set of sample songs. We train a Variational Autoencoder network to identify a low-dimensional set of variables that allows for the compression and representation of sample songs. By perturbing these variables with Perlin Noise— a temporally-consistent parameterized noise function—it is possible to generate smoothly-changing novel melodies. We show that (1) by regulating the amount of noise, one can specify how much of the base song will be preserved; and (2) there is a direct correlation between the noise signal and the differences between the statistical properties of novel melodies and the original one. Users can interpret the controllable noise as a type of “creativity knob”: the higher it is, the more leeway the network has to generate significantly different melodies. We present a physical prototype that allows musicians to use a keyboard to provide base melodies and to adjust the network’s “creativity knobs” to regulate in real-time the process that proposes new melody ideas. | |
dc.language | EN | |
dc.publisher | Universidade Federal do Rio Grande do Sul | |
dc.relation.ispartof | Proceedings of the International Conference on New Interfaces for Musical Expression | |
dc.relation.ispartofseries | Proceedings of the International Conference on New Interfaces for Musical Expression | |
dc.rights | Attribution 4.0 International | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.title | Parameterized Melody Generation with Autoencoders and Temporally-Consistent Noise | |
dc.type | Chapter | |
dc.creator.author | Weber, Aline | |
dc.creator.author | Alegre, Lucas N. | |
dc.creator.author | Tørresen, Jim | |
dc.creator.author | Castro da Silva, Bruno | |
cristin.unitcode | 185,15,5,42 | |
cristin.unitname | Forskningsgruppe for robotikk og intelligente systemer | |
cristin.ispublished | true | |
cristin.fulltext | original | |
dc.identifier.cristin | 1736189 | |
dc.identifier.bibliographiccitation | info:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.btitle=Music Proceedings of the International Conference on New Interfaces for Musical Expression&rft.spage=174&rft.date=2019 | |
dc.identifier.startpage | 174 | |
dc.identifier.endpage | 179 | |
dc.identifier.pagecount | 67 | |
dc.identifier.urn | URN:NBN:no-80503 | |
dc.type.document | Bokkapittel | |
dc.type.peerreviewed | Peer reviewed | |
dc.identifier.fulltext | Fulltext https://www.duo.uio.no/bitstream/handle/10852/77398/2/nime2019_paper035.pdf | |
dc.type.version | PublishedVersion | |
cristin.btitle | Music Proceedings of the International Conference on New Interfaces for Musical Expression | |
dc.relation.project | NFR/262762 | |
dc.relation.project | NFR/240862 | |
dc.relation.project | NFR/261645 | |