BioSeg: An open-source software for bioacoustic segmentation, cluster-assisted labeling, and dataset generation
SoftwareX, cilt.35, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 35
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.softx.2026.102902
- Dergi Adı: SoftwareX
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
- Anahtar Kelimeler: Bioacoustics, Bird sound segmentation, Dataset creation, HDBSCAN, Open-source software, UMAP
- Süleyman Demirel Üniversitesi Adresli: Evet
Özet
Bioacoustic research requires extensive manual effort to inspect, segment, and label large field recordings. We present BioSeg, an open-source research software designed to facilitate and streamline the manual labeling workflow of bird vocalizations. The software integrates waveform and spectrogram visualization, noise reduction, loudness normalization, and segmentation support to improve audibility in heterogeneous recordings. Optional UMAP-based dimensionality reduction and HDBSCAN clustering are provided as exploratory tools to assist grouping of acoustically similar segments, while expert listening remains essential. BioSeg enables structured, metadata-rich CSV export, supporting reproducible dataset preparation for ecological and machine learning applications.