SInES Tools: Sound Event Detector
(AI based sound event classification with YAMNet Model)


1. Click on " Start" to reset all values on default and wait for the AI Model to load entirely.
2. Upload one or multiple mp3 or wav audio file(s).
3. optional: If you have uploaded multiple audio files to analyze them in a batch:
   Additionally, export a table for each file containing all individual values over time as a .zip file
4. Click on " Analyse" to start the detection process.
5. optional (Single-File only): View the classified features in the plot. (Note: To maintain performance, only the Top
    20 sound events are visible by default. All 521 can be toggled in the legend.
)
6. Click on "Show JS Arrays" or "Export CSV", to display or export the recorded data.

Click "Start" to load the Models.

 Analysis Parameters: Window Size: 960 ms | Hop Size: 480 ms | Sample Rate (internal): 16000 Hz
Sound Event Detector © 2026 by Christoph Reuter and SInES (last modified: 13.9.2026) is released under MIT License
Translation of the Chinese version of the website: Li Hao
How to cite: Reuter, C. (2026). SInES Tools: Sound Event Detector. Web Application https://sinestools.univie.ac.at/yamnet_sounddetector.htm