Improving Polyphonic Music Models with Feature-Rich Encoding

11/26/2019
by   Omar Peracha, et al.
0

This paper explores sequential modeling 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 dataset, the model can either be conditioned on these features or trained to predict said features as extra components of the sequences being modeled. We show that training a neural network to predict a seemingly more complex sequence, with extra features included in the series being modeled, 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.

READ FULL TEXT
research
08/11/2021

Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding

This paper proposes a new self-attention based model for music score inf...
research
07/11/2020

Transformer-XL Based Music Generation with Multiple Sequences of Time-valued Notes

Current state-of-the-art AI based classical music creation algorithms su...
research
11/05/2020

From Note-Level to Chord-Level Neural Network Models for Voice Separation in Symbolic Music

Music is often experienced as a progression of concurrent streams of not...
research
04/28/2023

Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem

This paper targets the perceptual task of separating the different inter...
research
01/27/2023

Byte Pair Encoding for Symbolic Music

The symbolic music modality is nowadays mostly represented as discrete a...
research
12/29/2019

Approximating intractable short ratemodel distribution with neural network

We propose an algorithm which predicts each subsequent time step relativ...

Please sign up or login with your details

Forgot password? Click here to reset