Omar Peracha

Omar Peracha

High-quality datasets for learning-based modelling of polyphonic symbolic music remain less readily-accessible at scale than in other domains, such as language modelling or image classification. Deep learning algorithms show great potential for enabling the widespread use of interactive music generation technology in consumer applications, but the lack of large-scale datasets remains a bottleneck for the development of algorithms that can consistently generate high-quality outputs. We propose that models with narrow expertise can serve as a source of high-quality scalable synthetic data, and open-source the JS Fake Chorales, a dataset of 500 pieces generated by a new learning-based algorithm, provided in MIDI form. We take consecutive outputs from the algorithm and avoid cherry-picking in order to validate the potential to further scale this dataset on-demand. We conduct an online experiment for human evaluation, designed to be as fair to the listener as possible, and find that respondents were on average only 7% better than random guessing at distinguishing JS Fake Chorales from real chorales composed by JS Bach. Furthermore, we make anonymised data collected from experiments available along with the MIDI samples. Finally, we conduct ablation studies to demonstrate the effectiveness of using the synthetic pieces for research in polyphonic music modelling, and find that we can improve on state-of-the-art validation set loss for the canonical JSB Chorales dataset, using a known algorithm, by simply augmenting the training set with the JS Fake Chorales.

Omar Peracha

This paper explores sequential modelling of polyphonic music with deep neural networks. While recent breakthroughs have focussed on network architecture, we demonstrate that the representation of the sequence can make an equally significant contribution to the performance of the model as measured by validation set loss. By extracting salient features inherent to the training dataset, the model can either be conditioned on these features or trained to predict said features as extra components of the sequences being modelled. We show that training a neural network to predict a seemingly more complex sequence, with extra features included in the series being modelled, can improve overall model performance significantly. We first introduce TonicNet, a GRU-based model trained to initially predict the chord at a given time-step before then predicting the notes of each voice at that time-step, in contrast with the typical approach of predicting only the notes. We then evaluate TonicNet on the canonical JSB Chorales dataset and obtain state-of-the-art results.

Omar Peracha, Shawn Head

A common approach to generating symbolic music using neural networks involves repeated sampling of an autoregressive model until the full output sequence is obtained. While such approaches have shown some promise in generating short sequences of music, this typically has not extended to cases where the final target sequence is significantly longer, for example an entire piece of music. In this work we propose a network trained in an adversarial process to generate entire pieces of solo shakuhachi music, in the form of symbolic notation. The pieces are intended to refer clearly to traditional shakuhachi music, maintaining idiomaticity and key aesthetic qualities, while also adding novel features, ultimately creating worthy additions to the contemporary shakuhachi repertoire. A key subproblem is also addressed, namely the lack of relevant training data readily available, in two steps: firstly, we introduce the PH_Shaku dataset for symbolic traditional shakuhachi music; secondly, we build on previous work using conditioning in generative adversarial networks to introduce a technique for data augmentation.