A Topic Model for Melodic Sequences

TL;DR

This paper introduces the Variable-gram Topic Model for learning probabilistic representations of melodic sequences, effectively capturing complex temporal and statistical dependencies in music genre data.

Contribution

The paper presents a novel Variable-gram Topic Model that combines latent topics with contextual modeling for melodic sequences, improving predictive performance.

Findings

The model outperforms LDA, Topic Bigram, and related models in next-step prediction.

The novel evaluation method using Maximum Mean Discrepancy effectively assesses model-data distribution similarity.

The approach captures rich temporal and statistical dependencies in musical sequences.

Abstract

We examine the problem of learning a probabilistic model for melody directly from musical sequences belonging to the same genre. This is a challenging task as one needs to capture not only the rich temporal structure evident in music, but also the complex statistical dependencies among different music components. To address this problem we introduce the Variable-gram Topic Model, which couples the latent topic formalism with a systematic model for contextual information. We evaluate the model on next-step prediction. Additionally, we present a novel way of model evaluation, where we directly compare model samples with data sequences using the Maximum Mean Discrepancy of string kernels, to assess how close is the model distribution to the data distribution. We show that the model has the highest performance under both evaluation measures when compared to LDA, the Topic Bigram and related non-topic models.