mlsanityData to 7 Oct 2026

FMA: A Dataset For Music Analysis

arXiv 1612.01840 ↗First posted 6 Dec 2016cs.SD cs.IRcited by 205

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce the Free Music Archive (FMA), an open and easily accessible dataset suitable for evaluating several tasks in MIR, a field concerned with browsing, searching, and organizing large music collections. The community's growing interest in feature and end-to-end learning is however restrained by the limited availability of large audio datasets. The FMA aims to overcome this hurdle by providing 917 GiB and 343 days of Creative Commons-licensed audio from 106,574 tracks from 16,341 artists and 14,854 albums, arranged in a hierarchical taxonomy of 161 genres. It provides full-length and high-quality audio, pre-computed features, together with track- and user-level metadata, tags, and free-form text such as biographies. We here describe the dataset and how it was created, propose a train/validation/test split and three subsets, discuss some suitable MIR tasks, and evaluate some baselines for genre recognition. Code, data, and usage examples are available at https://github.com/mdeff/fma

Key facts. Cited by 205 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 15; 2023: 26; 2024: 38; 2025: 59; 2026: 52.

205 papers.

Sort:

By area:

  1. 2023MusicLM: Generating Music From Textcited by 442
  2. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 343
  3. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 215
  4. 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilitiescited by 183
  5. 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilitiescited by 127
  6. 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 124
  7. 2023Mustango: Toward Controllable Text-to-Music Generationcited by 100
  8. 2023Joint Audio and Speech Understandingcited by 99
  9. 2024Long-form music generation with latent diffusioncited by 88
  10. 2021Contrastive Learning of Musical Representationscited by 81
  11. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  12. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 70
38 more
  1. 2024Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversioncited by 58
  2. 2025DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignmentcited by 47
  3. 2024AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?cited by 46
  4. 2023WavMark: Watermarking for Audio Generationcited by 41
  5. 2025Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveycited by 38
  6. 2024Foundation Models for Music: A Surveycited by 34
  7. 2023LLark: A Multimodal Instruction-Following Language Model for Musiccited by 29
  8. 2023Controllable Music Production with Diffusion Models and Guidance Gradientscited by 29
  9. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  10. 2025InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialoguecited by 27
  11. 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesiscited by 25
  12. 2022Nystr"om Kernel Mean Embeddingscited by 21
  13. 2024AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generationcited by 21
  14. 2025Aligning Text-to-Music Evaluation with Human Preferencescited by 20
  15. 2024AudioMarkBench: Benchmarking Robustness of Audio Watermarkingcited by 19
  16. 2021Multi-Task Self-Supervised Pre-Training for Music Classificationcited by 18
  17. 2022Sound Localization by Self-Supervised Time Delay Estimationcited by 18
  18. 2023Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotationcited by 18
  19. 2024FLUX that Plays Musiccited by 18
  20. 2025The iNaturalist Sounds Datasetcited by 17
  21. 2025Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learningcited by 17
  22. 2021Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networkscited by 15
  23. 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
  24. 2022Where to Pay Attention in Sparse Training for Feature Selection?cited by 15
  25. 2025Benchmarking Music Generation Models and Metrics via Human Preference Studiescited by 15
  26. 2026Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Musiccited by 15
  27. 2024COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representationscited by 14
  28. 2024Benchmarking Representations for Speech, Music, and Acoustic Eventscited by 14
  29. 2021Learning music audio representations via weak language supervisioncited by 13
  30. 2023DISCO-10M: A Large-Scale Music Datasetcited by 13
  31. 2024Editing Music with Melody and Text: Using ControlNet for Diffusion Transformercited by 13
  32. 2024Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Roomscited by 12
  33. 2024Hearing Anything Anywherecited by 12
  34. 2025A2SB: Audio-to-Audio Schrodinger Bridgescited by 11
  35. 2025Discovering and Steering Interpretable Concepts in Large Generative Music Modelscited by 11
  36. 2021A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learningcited by 10
  37. 2023Brain2Music: Reconstructing Music from Human Brain Activitycited by 10
  38. 2023EnCodecMAE: Leveraging neural codecs for universal audio representation learningcited by 9

50 most cited of 205 All 205 (JSON)