Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.336976
Title: Towards an intelligent learning environment for melody composition through formalisation of Narmour's implication-realisation model
Author: Smith, Matthew Richard
ISNI:       0000 0000 8182 348X
Awarding Body: Open University
Current Institution: Open University
Date of Award: 1997
Availability of Full Text:
Access from EThOS:
Access from Institution:
Abstract:
This thesis describes research with the ultimate goal of finding ways to use artificial intelligence (AI) to encourage and facilitate melody composition by musical novices. The work described in this thesis forms the groundwork for the development of intelligent learning environments for novice composers in this domain. There were two stages to the research. The first stage was the formalisation and testing of an existing analytical theory of melody. This theory offers an explanation of how musical listeners break-up a melody into "chunks", and hear some notes as more important than others. The theory enables analysis of melodies in a hierarchical fashion. The formalisation process involved the implementation of a parser to create hierarchical analyses, and comparison of published analyses based on the theory with those created by the parser from the same melodies. From these results a critical evaluation of the analytical theory, and the parser, is presented. The second stage o f the research involved extending the parser with constraint-based generation techniques. One result is an AI tool (called MOTIVE), which can generate melodies given an analysis (from the parser, or constructed by the user) and a set of constraints to be applied at each hierarchical level. The features of the tool are presented, and a general architecture for an intelligent learning environment is proposed, within which MOTIVE would reside, which shows how the formalised analytical theory from the first part of the work could be used educationally by novice composers of melody.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.336976  DOI:
Keywords: Music theory
Share: