Computer Assisted Composition with Recurrent Neural Networks
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 2 months ago.

Computer Assisted Composition with Recurrent Neural Networks
Sequence modeling with neural networks has lead to powerful models of symbolic music data. We address the problem of exploiting these models to reach creative musical goals, by combining with human input. To this end we generalise previous work, which sampled Markovian sequence models under the constraint that the sequence belong to the language of a given finite state machine provided by the human. We consider more expressive nonMarkov models, thereby requiring approximate sampling which we provide in the form of an efficient sequential Monte Carlo method. In addition we provide and compare with a beam search strategy for conditional probability maximisation. Our algorithms are capable of convincingly reharmonising famous musical works. To demonstrate this we provide visualisations, quantitative experiments, a human listening test and audio examples. We find both the sampling and optimisation procedures to be effective, yet complementary in character. For the case of highly permissive constraint sets, we find that sampling is to be preferred due to the overly regular nature of the optimisation based results. The generality of our algorithms permits countless other creative applications.
Computer Assisted Composition with Recurrent Neural Networks
by Christian Walder, Dongwoo Kim
https://arxiv.org/pdf/1612.00092v2.pdf
You must be logged in to reply to this topic.