Dataset Strix: Audio Clips for Conflict Zone Sound Classification

Dataset Strix is a unified audio dataset for the STRIX project by the Proteus Group student association. It contains 2-second mono clips at 16 kHz for classifying sounds in conflict zones. The dataset was created by Tairooonz and last updated on June 12, 2026.

Use Cases

• Train a machine learning model to detect gunshots based on labeled audio clips.
• Develop a system for identifying drone presence based on acoustic signatures.
• Build a background noise classifier for filtering non-event sounds in surveillance audio.
• Benchmark audio event detection algorithms on military and conflict-related sounds.

Strengths

• Audio clips are standardized at 16 kHz and mono, which suggests consistent preprocessing.
• The dataset structure is organized into dedicated train and test folders for each class, facilitating model evaluation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

MAD (Military Audio Dataset) — June Wook Kim, Kaggle.

Collection Method

Likely aggregated and repackaged from the cited source for the STRIX project.

Freshness

Last updated 2026-06-12 23:18:36; freshness should be verified.