Real world neural networks for interactive music composition in real time

A new model designed for musicians to use as a tool for practicing and improvisation is developed based on a corpus of Jazz lead sheets. It is lightweight enough to work within the CPU and memory constraints of consumer equipment and operate in real time with input from a standard midi device. The m...

Full description

Bibliographic Details
Main Author: Bickerstaffe, Colin
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/48526/
_version_ 1848797784426151936
author Bickerstaffe, Colin
author_facet Bickerstaffe, Colin
author_sort Bickerstaffe, Colin
building Nottingham Research Data Repository
collection Online Access
description A new model designed for musicians to use as a tool for practicing and improvisation is developed based on a corpus of Jazz lead sheets. It is lightweight enough to work within the CPU and memory constraints of consumer equipment and operate in real time with input from a standard midi device. The model is also compatible for use on a Raspberry Pi for ultimate portability (at the cost of a significantly longer training time).
first_indexed 2025-11-14T20:09:23Z
format Dissertation (University of Nottingham only)
id nottingham-48526
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:09:23Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling nottingham-485262018-01-12T00:04:32Z https://eprints.nottingham.ac.uk/48526/ Real world neural networks for interactive music composition in real time Bickerstaffe, Colin A new model designed for musicians to use as a tool for practicing and improvisation is developed based on a corpus of Jazz lead sheets. It is lightweight enough to work within the CPU and memory constraints of consumer equipment and operate in real time with input from a standard midi device. The model is also compatible for use on a Raspberry Pi for ultimate portability (at the cost of a significantly longer training time). 2017-12-14 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/48526/1/Colin%20Bickerstaffe_MScDissertation.pdf Bickerstaffe, Colin (2017) Real world neural networks for interactive music composition in real time. [Dissertation (University of Nottingham only)] Artificial Neural Networks Recurrent Neural Networks Long Short Term Memory Musical Instrument Digital Interface.
spellingShingle Artificial Neural Networks
Recurrent Neural Networks
Long Short Term Memory
Musical Instrument Digital Interface.
Bickerstaffe, Colin
Real world neural networks for interactive music composition in real time
title Real world neural networks for interactive music composition in real time
title_full Real world neural networks for interactive music composition in real time
title_fullStr Real world neural networks for interactive music composition in real time
title_full_unstemmed Real world neural networks for interactive music composition in real time
title_short Real world neural networks for interactive music composition in real time
title_sort real world neural networks for interactive music composition in real time
topic Artificial Neural Networks
Recurrent Neural Networks
Long Short Term Memory
Musical Instrument Digital Interface.
url https://eprints.nottingham.ac.uk/48526/