mlsanityData to 7 Oct 2026

Symbolic music generation conditioned on continuous-valued emotions

arXiv 2203.16165 ↗First posted 30 Mar 2022eess.AS cs.AI cs.MMcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper we present a new approach for the generation of multi-instrument symbolic music driven by musical emotion. The principal novelty of our approach centres on conditioning a state-of-the-art transformer based on continuous-valued valence and arousal labels. In addition, we provide a new large-scale dataset of symbolic music paired with emotion labels in terms of valence and arousal. We evaluate our approach in a quantitative manner in two ways, first by measuring its note prediction accuracy, and second via a regression task in the valence-arousal plane. Our results demonstrate that our proposed approaches outperform conditioning using control tokens which is representative of the current state of the art.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 37 of its 71 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

37 of 71 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  8. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  9. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  10. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  11. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  12. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
25 more
  1. 2020Jukebox: A Generative Model for Musiccited by 535
  2. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 215
  3. 2018Music Transformercited by 207
  4. 2020Reformulating Unsupervised Style Transfer as Paraphrase Generationcited by 181
  5. 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
  6. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  7. 2016Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challengecited by 116
  8. 2020Towards Controllable Biases in Language Generationcited by 112
  9. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  10. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  11. 2017MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generationcited by 72
  12. 2018This Time with Feeling: Learning Expressive Musical Performancecited by 67
  13. 2019LakhNES: Improving multi-instrumental music generation with cross-domain pre-trainingcited by 54
  14. 2021EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generationcited by 53
  15. 2020Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature Modellingcited by 45
  16. 2019Counterpoint by Convolutioncited by 42
  17. 2020Learning Interpretable Representation for Controllable Polyphonic Music Generationcited by 40
  18. 2020Controlling Style in Generated Dialoguecited by 38
  19. 2019Encoding Musical Style with Transformer Autoencoderscited by 35
  20. 2019Deep Music Analogy Via Latent Representation Disentanglementcited by 31
  21. 2021Learning to Generate Music With Sentimentcited by 29
  22. 2020Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythmcited by 28
  23. 2017Audio Super Resolution using Neural Networkscited by 26
  24. 2020On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networkscited by 10
  25. 2020A variational autoencoder for music generation controlled by tonal tensioncited by 8

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 2; 2025: 3.

12 papers.

  1. 2023JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Modelscited by 41
  2. 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
  3. 2023AI-Based Affective Music Generation Systems: A Review of Methods, and Challengescited by 9
  4. 2023REMAST: Real-time Emotion-based Music Arrangement with Soft Transitioncited by 5
  5. 2023EmoGen: Eliminating Subjective Bias in Emotional Music Generationcited by 4
  6. 2023Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Datasetcited by 2
  7. 2025Video Soundtrack Generation by Aligning Emotions and Temporal Boundariescited by 2
  8. 2023EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Templatecited by 1
  9. 2025On the de-duplication of the Lakh MIDI datasetcited by 1
  10. 2023LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Musiccited by 0
  11. 2024Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distancecited by 0
  12. 2025AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generationcited by 0