Go to CAE-USC AI Modules

Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance

1 Functions

Audio Scene Description (CAE-ASD):

Receives Space-Time Audio Scene’s Space-Time.
Audio Object Input Audio Object.
Audio Scene Descriptors Possible Audio Scene to be augmented.
Computes Audio Objects Inside the input Audio Object.
Audio Scene Geometry Possible Audio Scene to be augmented.
Adds Audio Scene Descriptors To make the new Audio Scene.
Produces Audio Scene Descriptors (output) The augmented Audio Scene.

Unlike CAE-BAS that can only describe an Audio Scene composed of Audio Objects, CAE-ASD can describe an Audio Scene in terms of Audio Objects and Audio Scenes. In their turn, Audio Scene can be composed of Objects and Scenes.

2 Reference Model

Figure 1 depicts the Reference Architecture of the Audio Scene Description AIM.

Figure 1 – The Audio Scene Description (CAE-ASD) AIM

3 I/O Data

Table 1 – I/O Data of the Audio Scene Description (CAE‑ASD) AIM

Input Description
Space-Time Audio Objects Space-Time information.
Audio Object Multichannel Audio (with associated Microphone Array info)
Audio Scene Descriptors Input Audio Scene Descriptors
Output Description
Audio Scene Descriptors Output Audio Scene Descriptors

4 SubAIMs

4.1 Reference Model

Audio Scene Description (CAE-ASD) is a Composite AIM with the structure depicted in Figure 2.

Figure 2 – The Audio Scene Description (CAE-ASD) Composite AIM

The specification of the CAE-ASD Basic AIMs are provided at the links of Table 2.

4.2 Operation

4.3 Functions of SubAIMs

4.4 I/O Data of SubAIMs

4.5 AIMs and JSON Metadata

Table 2 provides the links to the AIM specifications and JSON schemas. AIM1 indicates the Composite AIM and AIM2 its SubAIMs.

Table 2 – AIMs and JSON Metadata of the Audio Scene Description (CAE‑ASD)

AIM1 AIM2 Name JSON
CAE‑ASD Audio Scene Description X
CAE‑AAT Audio Analysis Transform X
CAE‑ASL Audio Source Localisation X
CAE‑ASE Audio Separation and Enhancement X
CAE‑AST Audio Synthesis Transform X
CAE‑ADM Audio Descriptors Multiplexing X

5 JSON Metadata

https://schemas.mpai.community/CAE1/V2.5/AIMs/AudioSceneDescription.json

6 Profiles

No Profiles.

7 Reference Software

8 Conformance Testing

Table 3 – Conformance Testing Method for the Audio Scene Description (CAE‑ASD) AIM

Receives Space-Time Shall validate against Space-Time Schema.
Audio Object Shall validate against Audio-Object Schema.
Audio Data shall conform with Audio Data Qualifier.
Audio Scene Descriptors Shall validate against Audio Scene Descriptors Schema.
Produces Audio Scene Descriptors Shall validate against Audio Scene Descriptors Schema.

9 Performance Assessment

Go to CAE-USC AI Modules