Casey, Michael A.. 2003. Computational Creativity by Structural Analogy between Acoustic. Proceedings of AISB '03 Symposium on Artificial Intelligence and Creativity in Arts and Science, [Article]

No full text available

Abstract or Description

We present a method for generative modeling of audio content that performs mappings between minimum
entropy hidden Markov models learnt from audio data. By training with a minimum entropy prior, compact,
low-complexity models of the latent structure in audio source samples are obtained. Synthesis of new audio
content is achieved by mapping the state sequence of a nominated structure model onto a nominated content
model. The mapping is chosen such that the cross-entropies between the state variables of the nominated
models are minimised. This creates an analogy between the models’ structures, even when the specific content
of the models varies significantly. The re-mapped content state sequences are inverted to yield spectral vectors
that consist of the higher-order pattern information of the structure model and the low-order spectral features
of the content model. To illustrate the methods, we present examples of mapping audio structure and content
between drum beat samples in different styles.

Item Type:	Article
Departments, Centres and Research Units:	Computing
Dates:	Date Event April 2003 Published
Item ID:	15164
Date Deposited:	01 Dec 2015 15:27
Last Modified:	20 Jun 2017 09:43
Peer Reviewed:	Yes, this version has been peer-reviewed.
URI:	https://research.gold.ac.uk/id/eprint/15164

Edit Record (login required)