EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generation
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
Citing papers per year: 2021: 1; 2022: 7; 2023: 14; 2024: 10; 2025: 17; 2026: 4.
53 papers.
Sort:
By area:
- 2023MuseCoco: Generating Symbolic Music from Textcited by 50
- 2023Byte Pair Encoding for Symbolic Musiccited by 19
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processingcited by 15
- 2022Symbolic music generation conditioned on continuous-valued emotionscited by 12
- 2024PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Trainingcited by 12
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
- 2022Generating music with sentiment using Transformer-GANscited by 11
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
- 2025WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoningcited by 10
- 2023AI-Based Affective Music Generation Systems: A Review of Methods, and Challengescited by 9
- 2022ComMU: Dataset for Combinatorial Music Generationcited by 8
- 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Modelscited by 8
38 more
- 2022Conditional Drums Generation using Compound Word Representationscited by 7
- 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotationscited by 7
- 2024Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challengescited by 7
- 2025Towards Unified Music Emotion Recognition across Dimensional and Categorical Modelscited by 7
- 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detectioncited by 7
- 2023Impact of time and note duration tokenizations on deep learning symbolic music modelingcited by 6
- 2023REMAST: Real-time Emotion-based Music Arrangement with Soft Transitioncited by 5
- 2023N-Gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understandingcited by 5
- 2024Let Network Decide What to Learn: Symbolic Music Understanding Model Based on Large-scale Adversarial Pre-trainingcited by 5
- 2025ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Followingcited by 5
- 2023EmoGen: Eliminating Subjective Bias in Emotional Music Generationcited by 4
- 2023Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversationscited by 4
- 2024Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representationcited by 4
- 2024Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representationcited by 4
- 2025A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectivescited by 4
- 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributescited by 4
- 2022A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognitioncited by 3
- 2023IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio modelscited by 3
- 2023Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotionscited by 3
- 2025SyMuPe: Affective and Controllable Symbolic Music Performancecited by 3
- 2021Learning To Generate Piano Music With Sustain Pedalscited by 2
- 2023Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Datasetcited by 2
- 2023MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotioncited by 2
- 2024PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Textcited by 2
- 2025Video Soundtrack Generation by Aligning Emotions and Temporal Boundariescited by 2
- 2025Time-Shifted Token Scheduling for Symbolic Music Generationcited by 2
- 2023EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Templatecited by 1
- 2024MERGE -- A Bimodal Audio-Lyrics Dataset for Static Music Emotion Recognitioncited by 1
- 2025From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-trainingcited by 1
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understandingcited by 1
- 2025Assessing the Effectiveness of Membership Inference on Generative Musiccited by 1
- 2026PianoCoRe: Combined and Refined Piano MIDI Datasetcited by 1
- 2024Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distancecited by 0
- 2025Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Predictioncited by 0
- 2025AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generationcited by 0
- 2025Exploring How Audio Effects Alter Emotion with Foundation Modelscited by 0
- 2025Story2MIDI: Emotionally Aligned Music Generation from Textcited by 0
- 2025Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognitioncited by 0
50 most cited of 53 All 53 (JSON)
- 2026Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model5 Aug 2026
- 2026MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music16 Jul 2026
- 2026A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment28 Jun 2026
- 2026PianoCoRe: Combined and Refined Piano MIDI Dataset7 May 2026
- 2025Assessing the Effectiveness of Membership Inference on Generative Music25 Dec 2025
- 2025Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition16 Dec 2025
- 2025Story2MIDI: Emotionally Aligned Music Generation from Text1 Dec 2025
- 2025SyMuPe: Affective and Controllable Symbolic Music Performance5 Nov 2025
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding18 Oct 2025
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following27 Sep 2025
- 2025Exploring How Audio Effects Alter Emotion with Foundation Models18 Sep 2025
38 more
- 2025WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning5 Sep 2025
- 2025AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generation31 Aug 2025
- 2025Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction7 Jul 2025
- 2025From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training20 Jun 2025
- 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes21 May 2025
- 2025A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives1 Apr 2025
- 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detection24 Feb 2025
- 2025Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries14 Feb 2025
- 2025Towards Unified Music Emotion Recognition across Dimensional and Categorical Models6 Feb 2025
- 2024PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text4 Nov 2024
- 2024Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance23 Sep 2024
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing17 Sep 2024
- 2024Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation30 Jul 2024
- 2024Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation29 Jul 2024
- 2024Let Network Decide What to Learn: Symbolic Music Understanding Model Based on Large-scale Adversarial Pre-training11 Jul 2024
- 2024MERGE -- A Bimodal Audio-Lyrics Dataset for Static Music Emotion Recognition8 Jul 2024
- 2024PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training26 Jun 2024
- 2024Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges13 Jun 2024
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey27 Feb 2024
- 2023MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion16 Dec 2023
- 2023N-Gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding13 Dec 2023
- 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models21 Oct 2023
- 2023Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotions21 Oct 2023
- 2023Impact of time and note duration tokenizations on deep learning symbolic music modeling12 Oct 2023
- 2023EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template23 Sep 2023
- 2023Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations30 Aug 2023
- 2023Emotion4MIDI: a Lyrics-based Emotion-Labeled Symbolic Music Dataset27 Jul 2023
- 2023IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models24 Jul 2023
- 2023EmoGen: Eliminating Subjective Bias in Emotional Music Generation3 Jul 2023
- 2023MuseCoco: Generating Symbolic Music from Text31 May 2023
- 2023REMAST: Real-time Emotion-based Music Arrangement with Soft Transition14 May 2023
- 2023Byte Pair Encoding for Symbolic Music27 Jan 2023
- 2023AI-Based Affective Music Generation Systems: A Review of Methods, and Challenges10 Jan 2023
- 2022Generating music with sentiment using Transformer-GANs21 Dec 2022
- 2022ComMU: Dataset for Combinatorial Music Generation17 Nov 2022
- 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations14 Nov 2022
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search10 Aug 2022
- 2022Symbolic music generation conditioned on continuous-valued emotions30 Mar 2022
50 newest of 53 All 53 (JSON)
- 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Modelscited by 8
- 2023Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotionscited by 3
- 2026Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Modelcited by 0
- 2026Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model5 Aug 2026
- 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models21 Oct 2023
- 2023Fast Diffusion GAN Model for Symbolic Music Generation Controlled by Emotions21 Oct 2023
- 2023MuseCoco: Generating Symbolic Music from Textcited by 50
- 2023Byte Pair Encoding for Symbolic Musiccited by 19
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processingcited by 15
- 2022Symbolic music generation conditioned on continuous-valued emotionscited by 12
- 2024PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Trainingcited by 12
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
- 2022Generating music with sentiment using Transformer-GANscited by 11
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
- 2023AI-Based Affective Music Generation Systems: A Review of Methods, and Challengescited by 9
- 2022ComMU: Dataset for Combinatorial Music Generationcited by 8
- 2022Conditional Drums Generation using Compound Word Representationscited by 7
- 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotationscited by 7
12 most cited of 48 All 48 (JSON)
- 2026MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music16 Jul 2026
- 2026A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment28 Jun 2026
- 2026PianoCoRe: Combined and Refined Piano MIDI Dataset7 May 2026
- 2025Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition16 Dec 2025
- 2025Story2MIDI: Emotionally Aligned Music Generation from Text1 Dec 2025
- 2025SyMuPe: Affective and Controllable Symbolic Music Performance5 Nov 2025
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding18 Oct 2025
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025ABC-Eval: Benchmarking Large Language Models on Symbolic Music Understanding and Instruction Following27 Sep 2025
- 2025Exploring How Audio Effects Alter Emotion with Foundation Models18 Sep 2025
- 2025AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generation31 Aug 2025
- 2025Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction7 Jul 2025
12 newest of 48 All 48 (JSON)