> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cyberwave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Sound Security Guard (SSG)

> AST-based acoustic event detection for security and safety monitoring.

**Sound Security Guard** monitors audio for a **single active scenario** at a time using the pretrained [Audio Spectrogram Transformer](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) (`MIT/ast-finetuned-audioset-10-10-0.4593`). The model outputs 527 AudioSet class probabilities (multi-label sigmoid). No fine-tuning is required—scenarios map to existing AudioSet label strings.

## Strict scenario isolation

Only labels belonging to the selected scenario are evaluated. For example, with **Glass Break** active, a passing police siren is ignored even if the model detects it strongly.

## Scenarios (sub-modalities)

| Scenario                          | Monitored AudioSet labels (substring match)                                    |
| --------------------------------- | ------------------------------------------------------------------------------ |
| **Glass Break / Falling Objects** | Glass, Shatter, Smash crash, Thump, Crash, Bang                                |
| **Constant Alarm (Siren)**        | Alarm, Car alarm, Smoke detector, Siren, Ambulance (siren), Police car (siren) |
| **Help! / Screaming**             | Screaming, Yell, Shout, Children shouting                                      |
| **Custom**                        | User-defined comma-separated label substrings                                  |

## Parameters

| Parameter              | Default          | Description                                            |
| ---------------------- | ---------------- | ------------------------------------------------------ |
| `confidence_threshold` | `0.40`           | Alert when any scenario label exceeds this probability |
| `output_buffer_preset` | `speech-to-text` | Analysis window size (4 s recommended)                 |
| `output_buffer_size_s` | `4.0`            | Custom window length (seconds, min 1 s)                |
| `event_cooldown_s`     | `5.0`            | Minimum seconds between alerts                         |

## Input / output

**Input:** Same as VA—`audio` adapted to PCM S16LE int16 @ 16 kHz mono.

**Interim output (window filling / no alert):**

```json theme={null}
{
  "event_detected": false,
  "event_confidence": 0.12,
  "event_label": "",
  "event_type": "glass_break",
  "active_scenario": "glass_break",
  "sample_rate_hz": 16000,
  "channels": 1
}
```

**Alert output:**

```json theme={null}
{
  "audio": "<numpy int16 — analysis window>",
  "event_detected": true,
  "event_confidence": 0.67,
  "event_label": "Glass",
  "event_type": "glass_break",
  "active_scenario": "glass_break",
  "start_timestamp_sec": 8.0,
  "end_timestamp_sec": 12.0,
  "sample_rate_hz": 16000,
  "channels": 1
}
```

Wire `event_detected` to a `send_alert` node or conditional gate (see [Alerts](/feature-reference/edge/drivers/alerts)).

## Analysis window

Audio accumulates until the analysis window is full (default **4 s**), then AST runs inference. The buffer advances by **50% hop** (half-window overlap) so events near window boundaries are not missed. After an alert, a **cooldown** suppresses duplicate notifications.

## Example workflow

```
Audio Track → Audio Assistant (SSG, glass_break) → Send Alert
```

## Edge install

```bash theme={null}
pip install "cyberwave[ml-aed]"
```

First inference downloads the AST weights from Hugging Face.