Advanced Configurations

You can customize your detection results by modifying the advanced configurations in config.json.

1. Sensitivity Control

Sensitivity Control allows users to adjust the sensitivity so that it can be customized depending on target sounds and user scenarios. Sensitivity is adjustable on a scale from -2 (Very Low) to 2 (Very High). Default is 0 (Normal). Sensitivity can be set globally or individually per tag.

  • If certain tags are not being detected frequently, try increasing the sensitivity.
  • If you experience too many false detection, lowering the sensitivity may help.
sensitivity
"sensitivity_control": {
    "default_sensitivity": -1,
    "tag_sensitivity": {
        "Baby_cry": -2,
        "Gunshot": 1
    }
}

The configuration above sets the default sensitivity to -1 (LOW), but overrides the sensitivity for "Baby_cry" to -2 (VERY_LOW) and for "Gunshot" to 1 (HIGH).


2. Result Summary

Result Summary summarizes the prediction results by merging consecutive detection windows and returns the start time and duration of each detected sound tag.

The interval_margin parameter defines how much undetected duration between adjacent tags should still be considered part of a single event. This margin is applied globally to all tags by default, but it can also be overridden per tag to fine-tune behavior individually.

hope_size

"result_summary": {
    "default_interval_margin": 2,
    "tag_interval_margin": {
      "Baby_cry": 5,
      "Gunshot": 3
    }
}

The configuration above sets the global interval_margin to 2 seconds, but overrides the margin for "Baby_cry" to 5 seconds and for "Gunshot" to 3 seconds.

3. Tag Filter

Tag Filter allows users to control which sound tags should be included in the final output. This feature is useful when only a specific subset of tags is relevant for a given application or scenario.

To use this feature, define a list of tag names in the enabled_tags field. Only the tags in this list will appear in the output. If the list is empty, all detected tags will be included by default.

This filtering is applied after detection and does not affect the model’s internal inference process. It only controls which results are shown to the user. Filtering out tags does not reduce pricing, since pricing is determined by inference activity, not by output volume.

Tag filter
"tag_filter": {
    "enabled_tags": ["Music", "Speech"]
}

In this case, only detection of “Music" and “Speech" will be included in the final output. All other tags will be ignored.