The method we have developed is based on supervised sequence-to-sequence learning using recurrent neural networks (RNNs) and leverages a synthetic parallel (pairwise aligned) dataset generated for this purpose using existing accompaniment generation software. The focus of this thesis is on a family of tasks which we refer to as (one-shot) music style transfer, where the goal is to transfer the style of one musical piece or fragment onto another.In the first part of this work, we focus on supervised methods for symbolic music accompaniment style transfer, aiming to transform a given piece by generating a new accompaniment for it in the style of another piece. Recently, deep learning methods have enabled transforming musical material in a data-driven manner. The resulting model is available in our new open-source R package, ppm ( ). In three studies-one with artificially generated sequences, one with chord sequences from Western music, and one with new behavioral data from an auditory pattern detection experiment-we show how this decay kernel improves the model’s predictive performance for sequences whose underlying statistics change over time, and enables the model to capture effects of memory constraints on auditory pattern detection. We address these limitations with PPM-Decay, a new variant of PPM that introduces a customizable memory decay kernel. However, PPM has limitations as a cognitive model: in particular, it has a perfect memory that weights all historic observations equally, which is inconsistent with memory capacity constraints and recency effects observed in human cognition. A prominent computational model of these processes is Prediction by Partial Matching (PPM), a variable-order Markov model that learns by internalizing n -grams from training sequences. Statistical learning and probabilistic prediction are fundamental processes in auditory cognition.
0 kommentar(er)
