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

arXiv: https://arxiv.org/abs/2511.19342 · HTML: https://mlsanity.com/paper/2511.19342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Controllable deep melody generation via hierarchical music structure representation](https://mlsanity.com/paper/2109.00663/) (2021)
- [Computer-Generated Music for Tabletop Role-Playing Games](https://mlsanity.com/paper/2008.07009/) (2020)
- [Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework](https://mlsanity.com/paper/2104.13056/) (2021)
- [MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control](https://mlsanity.com/paper/2202.05528/) (2022)
- [XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework](https://mlsanity.com/paper/2501.08809/) (2025)
- [Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search](https://mlsanity.com/paper/2208.05162/) (2022)
- [A variational autoencoder for music generation controlled by tonal tension](https://mlsanity.com/paper/2010.06230/) (2020)
- [Controlling Surprisal in Music Generation via Information Content Curve Matching](https://mlsanity.com/paper/2408.06022/) (2024)
- [Midi Miner -- A Python library for tonal tension and track classification](https://mlsanity.com/paper/1910.02049/) (2019)
- [MoodLoopGP: Generating Emotion-Conditioned Loop Tablature Music with Multi-Granular Features](https://mlsanity.com/paper/2401.12656/) (2024)
- [Musical Form Generation](https://mlsanity.com/paper/2310.19842/) (2023)

## Abstract (arXiv)

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.