A Contextual Latent Space Model: Subsequence Modulation in Melodic Sequence

TL;DR

This paper introduces a new generative model called CLSM that enables more controlled and semantically meaningful exploration of subsequences in music sequences, improving interpolation smoothness and sample quality.

Contribution

The paper proposes a novel contextual latent space model that incorporates context-aware priors and encoders for enhanced subsequence generation and exploration in music.

Findings

Smoother interpolation in the latent space compared to baselines

Higher quality of generated music samples

Effective exploration of semantically similar subsequences

Abstract

Some generative models for sequences such as music and text allow us to edit only subsequences, given surrounding context sequences, which plays an important part in steering generation interactively. However, editing subsequences mainly involves randomly resampling subsequences from a possible generation space. We propose a contextual latent space model (CLSM) in order for users to be able to explore subsequence generation with a sense of direction in the generation space, e.g., interpolation, as well as exploring variations -- semantically similar possible subsequences. A context-informed prior and decoder constitute the generative model of CLSM, and a context position-informed encoder is the inference model. In experiments, we use a monophonic symbolic music dataset, demonstrating that our contextual latent space is smoother in interpolation than baselines, and the quality of generated samples is superior to baseline models. The generation examples are available online.