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

2025-11-24

AI Summary

This study addresses the challenge of explicit tonal tension control in symbolic music generation. We propose a tension-driven, two-level beam search framework that integrates an interval-vector-based tension computation model with a Transformer architecture. Joint optimization is performed at both the token level (to preserve diversity) and the bar level (to align generated outputs with a target tension curve), augmented by a tension-guided re-ranking mechanism. To our knowledge, this is the first approach enabling intuitive, precise, and interpretable control of tonal tension during AI composition—while supporting diverse stylistic realizations under identical tension contours. Objective evaluation demonstrates significantly improved tension regulation accuracy; subjective listening tests confirm that generated pieces exhibit both consistent tension evolution and high musical quality. Our work establishes a novel paradigm for controllable music generation.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Explicit control over tonal tension in symbolic music generation
• Integrating computational tension model with Transformer framework
• Ensuring generated music aligns with desired tension curves

Innovation

• Transformer framework with tonal tension model
• Two-level beam search for music generation
• Tension-based re-ranking aligns with target curve