# Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search

arXiv: https://arxiv.org/abs/2208.05162 · HTML: https://mlsanity.com/paper/2208.05162/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 10 Aug 2022.

## Builds on (most cited first, 12 of 12)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation](https://mlsanity.com/paper/2108.01374/) (2021)
- [MusPy: A Toolkit for Symbolic Music Generation](https://mlsanity.com/paper/2008.01951/) (2020)
- [Deep Music Analogy Via Latent Representation Disentanglement](https://mlsanity.com/paper/1906.03626/) (2019)
- [Learning to Generate Music With Sentiment](https://mlsanity.com/paper/2103.06125/) (2021)
- [Computer-Generated Music for Tabletop Role-Playing Games](https://mlsanity.com/paper/2008.07009/) (2020)
- [Generating Music from Literature](https://mlsanity.com/paper/1403.2124/) (2014)
- [On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns](https://mlsanity.com/paper/1910.09242/) (2019)

## Built on by (most cited first, 11 of 11)

- [MuseCoco: Generating Symbolic Music from Text](https://mlsanity.com/paper/2306.00110/) (2023)
- [AI-Based Affective Music Generation Systems: A Review of Methods, and Challenges](https://mlsanity.com/paper/2301.06890/) (2023)
- [EmoGen: Eliminating Subjective Bias in Emotional Music Generation](https://mlsanity.com/paper/2307.01229/) (2023)
- [Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation](https://mlsanity.com/paper/2407.20955/) (2024)
- [The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos](https://mlsanity.com/paper/2404.04420/) (2024)
- [Emotion-Conditioned Melody Harmonization with Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2306.03718/) (2023)
- [Situated Natural Language Explanations](https://mlsanity.com/paper/2308.14115/) (2023)
- [EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template](https://mlsanity.com/paper/2309.13259/) (2023)
- [Artificial ASMR: A Cyber-Psychological Approach](https://mlsanity.com/paper/2210.14321/) (2022)
- [Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance](https://mlsanity.com/paper/2409.15545/) (2024)
- [Explicit Tonal Tension Conditioning via Dual-Level Beam Search for Symbolic Music Generation](https://mlsanity.com/paper/2511.19342/) (2025)

## Abstract (arXiv)

This paper presents a new approach for controlling emotion in symbolic music generation with Monte Carlo Tree Search. We use Monte Carlo Tree Search as a decoding mechanism to steer the probability distribution learned by a language model towards a given emotion. At every step of the decoding process, we use Predictor Upper Confidence for Trees (PUCT) to search for sequences that maximize the average values of emotion and quality as given by an emotion classifier and a discriminator, respectively. We use a language model as PUCT's policy and a combination of the emotion classifier and the discriminator as its value function. To decode the next token in a piece of music, we sample from the distribution of node visits created during the search. We evaluate the quality of the generated samples with respect to human-composed pieces using a set of objective metrics computed directly from the generated samples. We also perform a user study to evaluate how human subjects perceive the generated samples' quality and emotion. We compare PUCT against Stochastic Bi-Objective Beam Search (SBBS) and Conditional Sampling (CS). Results suggest that PUCT outperforms SBBS and CS in almost all metrics of music quality and emotion.