Sound Classification
A type of the audio analyzer. Classifies the sound from the microphone input (or the speaker output) into one of the 521 AudioSet categories learned by Google's YAMNet model (speech, music, dog barking, alarms, glass breaking, screaming, car horns, and more). Used for abnormal sound detection and environmental sound analysis. The input is chosen in the analyzer setting Audio Source: Microphone (Input) or Speaker (Output).
Note
Audio analysis writes results only after the Start Analysis command is run
following Add Analysis.
Commands
| Command | Description |
|---|---|
| Specific Sound? | Checks whether the target sound is detected at or above the threshold. |
| Detection Result | Writes the name and probability of the most probable sound. |
| All Results | Writes every recognition result, ordered by probability, as JSON. |
Settings
| Setting | Description |
|---|---|
| Target Sound | The sound watched by Specific Sound?. One of the 521 categories (English names); the default is Speech. |
| Detection Threshold (%) | Probability at or above this value counts as the sound. 10 to 100, default 50. |
Output Variables
| Field | Type | Value |
|---|---|---|
| Sound Name | Text | English name of the most probable sound. |
| Sound Probability | Number | Probability of the recognized sound, 0 to 100. |
| Sound Detected | Digital | True when Specific Sound? finds the target sound at or above the threshold. |
| JSON Result | Text | Array of every recognition result. |
JSON Output
An array with, per result, label and confidence (0 to 100), ordered from the highest probability. Unlike Action Recognition and Hand Motion Recognition there is no index key.
[
{ "label": "Speech", "confidence": 85 },
{ "label": "Music", "confidence": 10 }
]
For the full list of the 521 categories see YAMNet's official class map (yamnet_class_map.csv).