Test and tune your impulse with realistic data
Loading results...
Clone this project to run performance calibration.
Select and save a config
Your impulse can be configured with a post-processing algorithm that will minimize
either false activations or false rejections. The chart shows a range of suggested
configs. If you save one, it will be used when your impulse is deployed.
Suggested config
Saved config
Selected config
Mean FAR
:
21.3%
Mean FRR
:
24.6%
Averaging window duration
:
834
ms
Detection threshold
:
0.73
Suppression period
:
982
ms
Performance overview
Shows the performance statistics for each label.
| Label | FAR | FRR | True positives | False positives | True negatives | False negatives |
|---|---|---|---|---|---|---|
| housesparrow | 54.2% | 23.8% | 115 | 180 | 152 | 36 |
| roseringedparakeet | 9.8% | 50% | 4 | 33 | 304 | 4 |
| testing | 0% | 0% | 0 | 0 | 319 | 0 |
Results for selected config
Shows any errors your impulse makes on a sample of data.
Loading audio sample...
Drag waveform to scroll
| Error | Type | Label | Start Time |
|---|
