HTMOneShotLoopClassification v1.0.0

Initial Release

This is the first public release of the HTMOneShotLoopClassification dataset.

Dataset Overview

• Total Samples: 5,561 electronic music samples (one-shots and loops)
• Categories: 8 stem types (kick, snare, hihat, bass, synth, vocal, percussion, fx)
• Features: 55 extracted audio features per sample
• Genres: House, Tech House, Minimal Techno
• Baseline Performance: 85.41% accuracy (SVM with RBF kernel)

What's Included

• Sample dataset CSV (100 rows)
• Complete metadata schema
• Documentation (README, dataset card, paper draft)
• Analysis scripts and visualizations
• Baseline classification results

Citation

If you use this dataset, please cite: x @dataset{hemimy2025htmoneshotloop, title={HTMOneShotLoopClassification: A Dataset of House, Tech House, and Minimal Techno Samples for Stem Category Classification}, author={Hemimy, Youssef}, year={2025}, publisher={Zenodo}, doi={10.5281/zenodo.17872190} }## License

This dataset is released under CC-BY-4.0 (Creative Commons Attribution 4.0 International).

Important: The CC-BY-4.0 license applies to the CSV dataset (extracted features and metadata), documentation, and scripts. The original audio files are NOT included and are NOT covered by this license. See LICENSING.md for details.

Links

• Documentation: See README.md for full documentation
• Dataset Card: See DATASET_CARD.md for HuggingFace-style dataset card
• Paper Draft: See docs/dataset_paper_draft.md

Acknowledgments

Dataset curated from professional electronic music sample packs. Features extracted using librosa audio analysis library.