Explicit Tonal Tension Conditioning via Dual-Level Beam Search for Symbolic Music Generation

TL;DR

This paper introduces a novel method for symbolic music generation that explicitly controls tonal tension using a dual-level beam search, combining a computational tension model with a Transformer to produce musically aligned outputs.

Contribution

The paper presents a new approach integrating a tonal tension model into a Transformer with a dual-level beam search for explicit tension control in music generation.

Findings

Effective modulation of tonal tension demonstrated

Generated music aligns with target tension curves

Method produces diverse musical interpretations

Abstract

State-of-the-art symbolic music generation models have recently achieved remarkable output quality, yet explicit control over compositional features, such as tonal tension, remains challenging. We propose a novel approach that integrates a computational tonal tension model, based on tonal interval vector analysis, into a Transformer framework. Our method employs a two-level beam search strategy during inference. At the token level, generated candidates are re-ranked using model probability and diversity metrics to maintain overall quality. At the bar level, a tension-based re-ranking is applied to ensure that the generated music aligns with a desired tension curve. Objective evaluations indicate that our approach effectively modulates tonal tension, and subjective listening tests confirm that the system produces outputs that align with the target tension. These results demonstrate that explicit tension conditioning through a dual-level beam search provides a powerful and intuitive tool to guide AI-generated music. Furthermore, our experiments demonstrate that our method can generate multiple distinct musical interpretations under the same tension condition.