A Predictive Model For Music Based On Learned Interval Representations

Abstract

Connectionist sequence models (e.g., RNNs) applied to musical sequences suffer from two known problems: First, they have strictly "absolute pitch perception". Therefore, they fail to generalize over musical concepts which are commonly perceived in terms of relative distances between pitches (e.g., melodies, scale types, modes, cadences, or chord types). Second, they fall short of capturing the concepts of repetition and musical form. In this paper we introduce the recurrent gated autoencoder (RGAE), a recurrent neural network which learns and operates on interval representations of musical sequences. The relative pitch modeling increases generalization and reduces sparsity in the input data. Furthermore, it can learn sequences of copy-and-shift operations (i.e. chromatically transposed copies of musical fragments)---a promising capability for learning musical repetition structure. We show that the RGAE improves the state of the art for general connectionist sequence models in learning

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylattner2018a

Related papers

• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• Multi-step Chord Sequence Prediction Based On Aggregated Multi-scale Encoder-decoder Network (2019)0.00
• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Learning Style-aware Symbolic Music Representations By Adversarial Autoencoders (2020)2.26
• A Recurrent Connectionist Model Of Melody Perception : An Exploration Using TRACX2 (2023)3.58
• Amadeus: Autoregressive Model With Bidirectional Attribute Modelling For Symbolic Music (2025)0.00
• Coupled Recurrent Models For Polyphonic Music Composition (2018)0.00
• Music Generation Based On Generative Adversarial Networks With Transformer (2023)0.00