# EmoGen: Eliminating Subjective Bias in Emotional Music Generation

arXiv: https://arxiv.org/abs/2307.01229 · HTML: https://mlsanity.com/paper/2307.01229/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs](https://mlsanity.com/paper/2101.02402/) (2021)
- [Video Background Music Generation with Controllable Music Transformer](https://mlsanity.com/paper/2111.08380/) (2021)
- [EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation](https://mlsanity.com/paper/2108.01374/) (2021)
- [Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation](https://mlsanity.com/paper/2210.10349/) (2022)
- [Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modelling](https://mlsanity.com/paper/2007.15474/) (2020)
- [MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE](https://mlsanity.com/paper/2105.04090/) (2021)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [Learning to Generate Music With Sentiment](https://mlsanity.com/paper/2103.06125/) (2021)
- [Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm](https://mlsanity.com/paper/2008.01291/) (2020)
- [Computer-Generated Music for Tabletop Role-Playing Games](https://mlsanity.com/paper/2008.07009/) (2020)
- [Symbolic music generation conditioned on continuous-valued emotions](https://mlsanity.com/paper/2203.16165/) (2022)
- [Music Composition with Deep Learning: A Review](https://mlsanity.com/paper/2108.12290/) (2021)
- [Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search](https://mlsanity.com/paper/2208.05162/) (2022)
- [Generating music with sentiment using Transformer-GANs](https://mlsanity.com/paper/2212.11134/) (2022)
- [On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns](https://mlsanity.com/paper/1910.09242/) (2019)
- [EmotionBox: a music-element-driven emotional music generation system using Recurrent Neural Network](https://mlsanity.com/paper/2112.08561/) (2021)
- [Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music Generation](https://mlsanity.com/paper/2209.07144/) (2022)

## Built on by (most cited first, 5 of 5)

- [Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation](https://mlsanity.com/paper/2407.20955/) (2024)
- [Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation](https://mlsanity.com/paper/2407.20176/) (2024)
- [Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance](https://mlsanity.com/paper/2409.15545/) (2024)
- [EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space](https://mlsanity.com/paper/2601.12079/) (2026)
- [Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation](https://mlsanity.com/paper/2608.03999/) (2026)

## Abstract (arXiv)

Music is used to convey emotions, and thus generating emotional music is important in automatic music generation. Previous work on emotional music generation directly uses annotated emotion labels as control signals, which suffers from subjective bias: different people may annotate different emotions on the same music, and one person may feel different emotions under different situations. Therefore, directly mapping emotion labels to music sequences in an end-to-end way would confuse the learning process and hinder the model from generating music with general emotions. In this paper, we propose EmoGen, an emotional music generation system that leverages a set of emotion-related music attributes as the bridge between emotion and music, and divides the generation into two stages: emotion-to-attribute mapping with supervised clustering, and attribute-to-music generation with self-supervised learning. Both stages are beneficial: in the first stage, the attribute values around the clustering center represent the general emotions of these samples, which help eliminate the impacts of the subjective bias of emotion labels; in the second stage, the generation is completely disentangled from emotion labels and thus free from the subjective bias. Both subjective and objective evaluations show that EmoGen outperforms previous methods on emotion control accuracy and music quality respectively, which demonstrate our superiority in generating emotional music. Music samples generated by EmoGen are available via this link:https://ai-muzic.github.io/emogen/, and the code is available at this link:https://github.com/microsoft/muzic/.