1 Version
V2.1
2 Functions
Audio Scene Description (CAE-ASD):
- Receives the Audio Scene composed of:
- Microphone Array Geometry.
- Multichannel Audio, i.e., the output of the Microphone Array.
- Separates Audio Objects.
- Produces Audio Scene Descriptors.
3 Reference Architecture
Figure 12 depicts the Reference Architecture of the Audio Scene Description AIM.

Figure 12 – The Audio Scene Description Composite AIM
4 I/O Data
Table specifies the Input and Output Data of the Audio Scene Description AIM.
Table – I/O Data of Audio Scene Description
| Input | Description |
| Microphone Array Geometry | The description of the spatial microphone arrangement. |
| Multichannel Audio | The Audio generated by the Microphone Array. |
| Output | Description |
| Audio Scene Descriptors | The combination of Audio Scene Geometry and Audio Objects. |
5 SubAIMs
| Audio Analysis Transform |
| Audio Source Localisation |
| Audio Separation and Enhancement |
| Audio Synthesis Transform |
| Audio Descriptor Multiplexing |
5 JSON Metadata
https://schemas.mpai.community/CAE/V2.1/AIMs/AudioSceneDescription.json