Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance
1 Functions
The Enhanced Audio Multiplexing (PGM‑EAM) AI Module consolidates the perceptual and enriched per‑object evidence of an audio scene into a single Enhanced Audio Scene Descriptors representation by
- Aligning each derived attribute (motion, proximity, acoustic environment, object type, salience) with the corresponding Audio Object
- Consolidating the aligned evidence into the Enhanced Audio Scene Descriptors
- Preserving consistency across motion, proximity, acoustic, identity, and salience information
- Emitting the execution status
The EAM AI Module operates as follows:
- Receives the Audio Objects together with the Audio Scene Descriptors (carrying the Motion Flags and Proximity Class of each Audio Object) and the per‑object enrichment signals — Acoustic Profile and Audio Object Type — and the Salience Results
- Aligns each derived attribute with the Audio Object it qualifies
- Consolidates the aligned evidence into the Enhanced Audio Scene Descriptors
- Emits the Audio CXT Response
The module does not derive new evidence; it composes the outputs of the upstream enrichment SubAIMs into the final audio scene description.
2 Reference Model
Figure 1 depicts the Reference Model of the Enhanced Audio Multiplexing (PGM‑EAM) AIM.
Figure 1 – The Enhanced Audio Multiplexing (PGM‑EAM) AIM
3 I/O Data
Table 1 specifies the Input and Output Data of the Enhanced Audio Multiplexing (PGM‑EAM) AIM.
| Input | Description |
|---|---|
| Audio Object | The audio objects of the scene to which the derived attributes are attached. |
| Audio Scene Descriptors | The Audio Scene Descriptors produced by Audio Scene Description, carrying the Motion Flags and Proximity Class of each Audio Object. |
| Acoustic Profile | Environmental acoustic characterisation produced by Acoustic Environment Analysis. |
| Audio Object Types | Semantic object‑type label produced by Audio Object Identification. |
| Salience Results | Ranked Audio Objects and Filtered Salient Audio Objects produced by Audio Salience Mapping. |
| Output | Description |
| Enhanced Audio Scene Descriptors | The audio scene description with all derived and semantic attributes consolidated per Audio Object. |
| Audio CXT Response | Response describing the execution and outcome of Enhanced Audio Multiplexing processing. |
| Audio Domain Request | |
| Audio Interaction History Request |
4 SubAIMs
No SubAIMs.
5 JSON Metadata
https://schemas.mpai.community/PGM1/V1.0/AIMs/EnhancedAudioMultiplexing.json
6 Profiles
No Profiles.
7 Reference Software
Not part of this specification.
8 Conformance Testing
Table 2 provides the Conformance Testing Method for the Enhanced Audio Multiplexing (PGM‑EAM) AIM.
If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present, and conform with the Qualifier, if present.
| Receives | Audio Object | Shall validate against Audio Object schema. |
| Audio Scene Descriptors | Shall validate against Audio Scene Descriptors schema. | |
| Acoustic Profile | Shall validate against Acoustic Profile schema. | |
| Audio Object Types | Shall validate against Audio Object Types schema. | |
| Salience Results | Shall validate against Salience Results schema. | |
| Produces | Enhanced Audio Scene Descriptors | Shall validate against Enhanced Audio Scene Descriptors schema. |
| Audio CXT Response | Shall validate against Audio CXT Response schema. |
9 Performance Assessment
Not part of this specification.
