Show simple item record

dc.contributor.authorCHOI, Ken_US
dc.contributor.authorsandler, Men_US
dc.contributor.authorfazekas, Gen_US
dc.contributor.authorConference on Computer Simulation of Musical Creativityen_US
dc.date.accessioned2016-05-26T13:05:46Z
dc.date.available2016-04-15en_US
dc.date.issued2016-06-18en_US
dc.date.submitted2016-04-27T17:15:18.771Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/12552
dc.description.abstractIn this paper, we introduce new methods and discuss results of text-based LSTM (Long Short-Term Memory) networks for automatic music composition. The proposed network is designed to learn relationships within text documents that represent chord progressions and drum tracks in two case studies. In the experiments, word-RNNs (Recurrent Neural Networks) show good results for both cases, while character-based RNNs (char-RNNs) only succeed to learn chord progressions. The proposed system can be used for fully automatic composition or as semi-automatic systems that help humans to compose music by controlling a diversity parameter of the model.en_US
dc.rightsarXiv record http://arxiv.org/abs/1604.05358. Presented at Conference on Computer Simulation of Musical Creativity
dc.subjectautomatic compositionen_US
dc.subjectlstmen_US
dc.subjectrnnen_US
dc.subjectalgorithmic compositionen_US
dc.titleText-based LSTM networks for Automatic Music Compositionen_US
dc.typeConference Proceeding
pubs.notesNo embargoen_US
pubs.publication-statusAccepteden_US
dcterms.dateAccepted2016-04-15en_US
qmul.funderFusing Semantic and Audio Technologies for Intelligent Music Production and Consumption::Engineering and Physical Sciences Research Councilen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record