Experimental Results for Music Genre Classification on GTZAN, FMA-Small, and FMA-Medium
by Yunyan Ma·Updated 1mo ago
5.5 KB1files
Available on 1 platform
Sign in to view source links and access this dataset
Description
CT-GateNet, a hybrid neural network architecture, achieved classification accuracies of 98.72%, 89.42%, and 69.07% on the GTZAN, FMA-SMALL, and FMA-Medium music genre datasets, respectively. The 5.5 KB Excel file contains experimental datasets from this research, authored by Yunyan Ma and last updated in April 2026. The data is shared under a CC-BY-4.0 license on figshare.
Use Cases
Benchmarking new music genre classification models based on the reported accuracy scores.
Analyzing the performance of hybrid neural network architectures like CT-GateNet on public datasets.
Investigating the impact of data augmentation strategies, such as denoising diffusion models, on classification tasks.
Comparing model generalization capabilities across datasets of different scales (e.g., GTZAN vs. FMA-Medium).
Strengths
Provides concrete performance metrics (e.g., 98.72% accuracy on GTZAN) for model validation.
Results are derived from experiments on three established public datasets: GTZAN, FMA-SMALL, and FMA-Medium.
Shared under a permissive CC-BY-4.0 license, allowing for reuse and redistribution.
Limitations
Row count and column-level documentation are unknown, limiting suitability assessment.
The 5.5 KB file size suggests the dataset contains summary results, not the underlying audio features or raw data.
Description metadata is limited; actual data structure and content require manual inspection after download.
Provenance
Source
figshare, authored by Yunyan Ma.
Collection Method
Experimental results from a research paper proposing the CT-GateNet architecture.
Time Range
The dataset itself was last updated in 2026; the temporal coverage of the underlying music data is unknown.
Freshness
Last updated 2026-04-09 17:37:55; freshness should be verified.
Geography
Spatial coverage is not specified.
The dataset is a 5.5 KB Excel (XLS) file containing summary results, not the original audio files or feature vectors.