mlsanityData to 7 Oct 2026

EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation

arXiv 2108.01374 ↗First posted 3 Aug 2021cs.SD cs.MM eess.AScited by 53

Not on the map. Why?

Abstract (arXiv)

While there are many music datasets with emotion labels in the literature, they cannot be used for research on symbolic-domain music analysis or generation, as there are usually audio files only. In this paper, we present the EMOPIA (pronounced `yee-m`o-pi-uh') dataset, a shared multi-modal (audio and MIDI) database focusing on perceived emotion in pop piano music, to facilitate research on various tasks related to music emotion. The dataset contains 1,087 music clips from 387 songs and clip-level emotion labels annotated by four dedicated annotators. Since the clips are not restricted to one clip per song, they can also be used for song-level analysis. We present the methodology for building the dataset, covering the song list curation, clip selection, and emotion annotation processes. Moreover, we prototype use cases on clip-level music emotion classification and emotion-based symbolic music generation by training and evaluating corresponding models using the dataset. The result demonstrates the potential of EMOPIA for being used in future exploration on piano emotion-related MIR tasks.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Aug 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 14; 2024: 10; 2025: 17; 2026: 4.

53 papers.

Sort:

By area:

  1. 2023MuseCoco: Generating Symbolic Music from Textcited by 50
  2. 2023Byte Pair Encoding for Symbolic Musiccited by 19
  3. 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processingcited by 15
  4. 2022Symbolic music generation conditioned on continuous-valued emotionscited by 12
  5. 2024PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Trainingcited by 12
  6. 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
  7. 2022Generating music with sentiment using Transformer-GANscited by 11
  8. 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
  9. 2025WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoningcited by 10
  10. 2023AI-Based Affective Music Generation Systems: A Review of Methods, and Challengescited by 9
  11. 2022ComMU: Dataset for Combinatorial Music Generationcited by 8
  12. 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Modelscited by 8
38 more
  1. 2022Conditional Drums Generation using Compound Word Representationscited by 7
  2. 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotationscited by 7
  3. 2024Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challengescited by 7
  4. 2025Towards Unified Music Emotion Recognition across Dimensional and Categorical Modelscited by 7
  5. 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detectioncited by 7
  6. 2023Impact of time and note duration tokenizations on deep learning symbolic music modelingcited by 6
  7. 2023REMAST: Real-time Emotion-based Music Arrangement with Soft Transitioncited by 5
  8. 2023N-Gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understandingcited by 5
  9. 2024Let Network Decide What to Learn: Symbolic Music Understanding Model Based on Large-scale Adversarial Pre-trainingcited by 5
  10. 2025ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Followingcited by 5
  11. 2023EmoGen: Eliminating Subjective Bias in Emotional Music Generationcited by 4
  12. 2023Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversationscited by 4
  13. 2024Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representationcited by 4
  14. 2024Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representationcited by 4
  15. 2025A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectivescited by 4
  16. 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributescited by 4
  17. 2022A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognitioncited by 3
  18. 2023IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio modelscited by 3
  19. 2023Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotionscited by 3
  20. 2025SyMuPe: Affective and Controllable Symbolic Music Performancecited by 3
  21. 2021Learning To Generate Piano Music With Sustain Pedalscited by 2
  22. 2023Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Datasetcited by 2
  23. 2023MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotioncited by 2
  24. 2024PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Textcited by 2
  25. 2025Video Soundtrack Generation by Aligning Emotions and Temporal Boundariescited by 2
  26. 2025Time-Shifted Token Scheduling for Symbolic Music Generationcited by 2
  27. 2023EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Templatecited by 1
  28. 2024MERGE -- A Bimodal Audio-Lyrics Dataset for Static Music Emotion Recognitioncited by 1
  29. 2025From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-trainingcited by 1
  30. 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understandingcited by 1
  31. 2025Assessing the Effectiveness of Membership Inference on Generative Musiccited by 1
  32. 2026PianoCoRe: Combined and Refined Piano MIDI Datasetcited by 1
  33. 2024Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distancecited by 0
  34. 2025Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Predictioncited by 0
  35. 2025AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generationcited by 0
  36. 2025Exploring How Audio Effects Alter Emotion with Foundation Modelscited by 0
  37. 2025Story2MIDI: Emotionally Aligned Music Generation from Textcited by 0
  38. 2025Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognitioncited by 0

50 most cited of 53 All 53 (JSON)