Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.657842
Title: Sound design : an artificial intelligence approach
Author: Miranda, Eduardo Reck
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 1995
Availability of Full Text:
Access through EThOS:
Full text unavailable from EThOS. Please try the link below.
Access through Institution:
Abstract:
Modern computer technology enables the production of a virtually limitless variety of sounds by providing substantial access to the parameter settings of synthesis algorithms. However, the design of sounds using a synthesis algorithm is still accomplished in a very old-fashioned way: by feeding the algorithm with streams of numerical data. Furthermore, these numbers are usually worked out manually. For example, a composer who works with the Csound synthesis programming language must master Csound for implementing a synthesis algorithm and also specify all the input parameter values for the production of every single sound. Depending on the complexity of the algorithm, there might be cases where over a hundred parameters need to be specified for each sound event. In such a situation the imagination of the composer can easily become vulnerable to time-consuming, non-musical tasks. We argue that the power of the computer could also provide better ways for the composer to express his requests to the synthesis algorithm at hand and moreover, provide appropriate aid for the exploration of sonic ideas. To this end, we propose an Artificial Intelligence (AI) approach to sound design systems, which focuses on sound design as a knowledge-based kind of intelligent behaviour. We consider that sound design involves the explicit organisation, application and generation of knowledge. AI is aimed here at helping the composer to handle this knowledge by means of suitable knowledge representation and machine learning techniques.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.657842  DOI: Not available
Share: