# The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use

arXiv: https://arxiv.org/abs/1306.1461 · HTML: https://mlsanity.com/paper/1306.1461/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2013.

## Built on by (most cited first, 11 of 11)

- [JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation](https://mlsanity.com/paper/2512.22905/) (2025)
- [DISCO-10M: A Large-Scale Music Dataset](https://mlsanity.com/paper/2306.13512/) (2023)
- [WikiMuTe: A web-sourced dataset of semantic descriptions for music audio](https://mlsanity.com/paper/2312.09207/) (2023)
- [Data leakage in cross-modal retrieval training: A case study](https://mlsanity.com/paper/2302.12258/) (2023)
- [On the de-duplication of the Lakh MIDI dataset](https://mlsanity.com/paper/2509.16662/) (2025)
- [Continuous Audio Thinking for Large Audio Language Models](https://mlsanity.com/paper/2606.18273/) (2026)
- [MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms](https://mlsanity.com/paper/2104.02309/) (2021)
- [The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification](https://mlsanity.com/paper/2409.17069/) (2024)
- [A quest through interconnected datasets: lessons from highly-cited ICASSP papers](https://mlsanity.com/paper/2410.03676/) (2024)
- [Style-based Composer Identification and Attribution of Symbolic Music Scores: a Systematic Survey](https://mlsanity.com/paper/2506.12440/) (2025)
- ["I made this (sort of)": Negotiating authorship, confronting fraudulence, and exploring new musical spaces with prompt-based AI music generation](https://mlsanity.com/paper/2507.23365/) (2025)

## Abstract (arXiv)

The GTZAN dataset appears in at least 100 published works, and is the most-used public dataset for evaluation in machine listening research for music genre recognition (MGR). Our recent work, however, shows GTZAN has several faults (repetitions, mislabelings, and distortions), which challenge the interpretability of any result derived using it. In this article, we disprove the claims that all MGR systems are affected in the same ways by these faults, and that the performances of MGR systems in GTZAN are still meaningfully comparable since they all face the same faults. We identify and analyze the contents of GTZAN, and provide a catalog of its faults. We review how GTZAN has been used in MGR research, and find few indications that its faults have been known and considered. Finally, we rigorously study the effects of its faults on evaluating five different MGR systems. The lesson is not to banish GTZAN, but to use it with consideration of its contents.