Use this URL to cite or link to this record in EThOS:
Title: Remembering the future : genetic co-evolution and MPEG7 matching in the creation of artificial music improvisors
Author: Casal, David Plans
ISNI:       0000 0004 2669 3466
Awarding Body: University of East Anglia
Current Institution: University of East Anglia
Date of Award: 2008
Availability of Full Text:
Access from EThOS:
This dissertation proposes the following thesis: that the combination of genetic coevolution and use of spectral analysis is a feasible method for designing an interactive musical algorithm. It also proposes that algorithm designers in this field must take the computational representation and use of time as a phenomena to heart, when designing algorithmic systems that mean to engage in such a complex time domain as music-making. Musical improvisation is driven mainly by the unconscious mind, to reference the entire cultural heritage of an improvisor in a single flash. This thesis introduces a case study of evolutionary computation techniques, in particular genetic co-evolution, as applied to the frequency domain using MPEG7 techniques, in order to create an articial agent that mediates between an improvisor and her unconscious mind, to probe and unblock improvisatory action in live music performance or practice. However, in the experience of musical improvisation with an artificial improvisor. a performer experiences diff\erance. As every musical intention is given by the human player to the live algorithm driving the artificial player (and viceversa), meaning can never be frilly conveyed but for the opposition of other, differing musical intentions. However, neither algorithm nor human can for now, successfully convey the emotional consequence of this diff\'erance to each other, and thus the human player is left to invest into and create a prosthetic emotional relationship. The rest of the dissertation will outline the emotional problem space engendered by the author's interaction with an algorithm over a period of two years' musical performances, and explicate a brute-force solution designed to foreshorten the emotional distance between algorithm and human.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available