DYCI2
Dynamiques créatives de l'interaction improvisée -- Creative Dynamics of Improvised Interaction
Guiding Factor Oracle Improvisation With a Probabilistic Model
Here, we compare improvisations generated with a Factor Oracle alone vs. improvisations generated with a Factor Oracle combined with a probabilistic model. The probabilistic model is an optimised interpolation of smoothed sub-models learnt on a corpus.
In the following examples, the probabilistic sub-models used are a bigram on the melody and a model representing the correlations between the melody and the harmony.
The training corpus is Charlie Parker's Omnibook (database available here). It has been divided into 3 sub-corpora : a training corpus to estimate the sub-models probabilities; a validation corpus to optimise the interpolation and smoothing coefficients of the probabilistic model; and a test corpus.
The Factor Oracles are constructed on a single tune from the test corpus.
Examples on Anthropology :
Without a probabilistic model :
With a probabilistic model :
Examples on Donna Lee :
Without a probabilistic model :
With a probabilistic model :