BioSeg: An open-source software for bioacoustic segmentation, cluster-assisted labeling, and dataset generation
SoftwareX · 2026-09 · 35 · 102902
DOI: 10.1016/j.softx.2026.102902 ↗Kurz gefasst
Fachartikel in der Zeitschrift SoftwareX, 2026-09. Verfasst von Gökhan Turan und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Scientific and Technological Research Council of Turkey.
Abstract (Originalsprache)
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.
Förderung
- Scientific and Technological Research Council of Turkey
Zitieren
APA
Turan, G., Küçüksille, E. U., & Süel, H. (2026). BioSeg: An open-source software for bioacoustic segmentation, cluster-assisted labeling, and dataset generation. SoftwareX, 35, 102902. https://doi.org/10.1016/j.softx.2026.102902
Vancouver
Turan G, Küçüksille EU, Süel H. BioSeg: An open-source software for bioacoustic segmentation, cluster-assisted labeling, and dataset generation. SoftwareX. 2026;35:102902. doi:10.1016/j.softx.2026.102902
BibTeX
@article{Turan2026,
author = {Turan, Gökhan and Küçüksille, Ecir Uğur and Süel, Halil},
title = {BioSeg: An open-source software for bioacoustic segmentation, cluster-assisted labeling, and dataset generation},
journal = {SoftwareX},
year = {2026},
volume = {35},
pages = {102902},
doi = {10.1016/j.softx.2026.102902}
}
EUVIMED