Zebra Finch Vocalization Dataset for Semi-Automated Clustering

Abstract
This dataset contains vocalization data from adult male Zebra Finches (Taeniopygia guttata), specialized for evaluating clustering methods of vocal elements. It includes segmented spectrograms, uniform manifold approximation and projection (UMAP) embeddings, and cluster assignments derived from manual validation, fully automated algorithms, and semi-automated workflows.

Dataset Content
The dataset covers three subjects (R3406, R3640, R3822) and features:
- HDF5 Archives: Optimized data structures containing syllable segments, audio spectrogram features, and UMAP coordinates (`umap_x`, `umap_y`).

Subjects
- Species: Zebra Finch (Taeniopygia guttata)
- IDs: R3406, R3640, R3822

Usage & Code
This dataset is designed for use with the "Semi-Automated Clustering Tool", a Python-based GUI developed for efficient refinement of vocal clusters.
- Code Repository: https://github.com/hwiora/semi_automated_clustering/
- Documentation: Refer to the repository `README.md` for instructions on loading this data and running the visualization tool.