Function Reference Model Input/Output Data
SubAIMs JSON Metadata Profiles

1. Function

The Audio Scene Enhancement (PGM-ASE) AIM performs interpretative enrichment of an audio scene captured by Context Capture, in order to derive additional, non‑perceptual audio properties relevant to spatial understanding, interaction, and user‑centric reasoning.

ASE operates on Audio SUD Directive received from A-User Control, Audio Scene Descriptors (ASD) received from Context Capture, and Audio Domain Response resulting from queries made to Domain Access and produces Audio SUD Status sent to A-User Control, Enhanced Audio Scene Descriptors sent to Prompt Creation and Audio Domain Request when querying Domain Access.

Enhanced Audio Scene Descriptors  preserve the original perceptual semantics while augmenting them with derived and semantic information under directive control.

 

2. Reference Model

Figure 1 gives the of Audio Scene Enhancement (PGM-ASE) AIM Reference Model.

Figure 1 – The Reference Model of the Audio Scene Enhancement (PGM-ASE) AIM

3. Input/Output Data

Table 1 gives the Input/Output Data of the Audio Scene Enhancement (PGM-ASE) AIM.

Table 1 – Input/Output Data of the Audio Scene Enhancement (PGM-ASE) AIM

Input Description
Audio Scene Descriptors Perceptual description of the audio scene produced by Context Capture.
Audio SUD Directive Control directives specifying scope, depth, or policy constraints for audio enhancement.
Audio Domain Request Domain‑specific knowledge supporting audio interpretation and semantic classification.
Output Description
Enhanced Audio Scene Descriptors Audio Scene Descriptors augmented with derived and semantic audio properties produced by ASE.
Audio SUD Status Status information describing the execution and outcome of Audio Scene Enhancement processing.
Audio Domain Response Response to Domain‑specific knowledge request.

4. SubAIMs (informative)

An Audio Scene Enhancement (PGM-ASE) AIM implementation may adopt the architecture of Figure 2.

Figure 2 -Reference Model of the Composite Audio Spatial Reasoning (PGM-ASR) AIM.

Table 2 specifies the Functions performed by PGM-ASP AIM’s SubAIMs in the current example.

Table 2 – Functions performed by Audio Scene Enhancement (PGM-ASE) AIM s SubAIMs

SubAIM Specification Purpose Input Data Output Data
Audio Descriptor Parsing Structures raw Audio Scene Descriptors into explicit Audio Objects and spatial attributes without semantic interpretation. Audio Scene Descriptors
Audio SUD Directive		 Audio Objects
Spatial Attitudes
Audio SUD Status
Audio Motion & Proximity Analysis Detects temporal and spatial dynamics of audio objects by tracking their evolution in space and time. Audio Objects
Spatial Attitudes		 Motion Flags (e.g. stationary, moving)
Proximity Class (e.g. near, mid, far)
Acoustic Environment Analysis Characterises the acoustic conditions affecting audio objects using signal‑derived measures. Audio Objects
Spatial Attitudes		 Acoustic Profile (e.g. reverberation, ambient noise, spectral characteristics)
Audio Object Identification Assigns semantic object type labels to audio objects using classification models and optional domain knowledge. Audio Objects
Spatial Attitudes
Domain Response		 Audio Object Type (e.g. speech, music, alarm)
Type Confidence
Audio Salience Mapping Determines the relative relevance of audio objects with respect to user interaction and context. Motion Flags
Proximity Class
Acoustic Profile
Audio Object Type
Audio SUD Directive
Domain Response		 Ranked Audio Objects
Filtered Salient Audio Objects
Audio Output Construction Aggregates perceptual and enriched evidence into Enhanced Audio Scene Descriptors and emits execution status. Audio Objects
Spatial Attitudes
Motion Flags
Proximity Class
Acoustic Profile
Audio Object Type
Salience Results		 Enhanced Audio Scene Descriptors (Enhanced ASD)
Audio SUD Status

5. JSON Metadata

https://schemas.mpai.community/PGM1/V1.0/AIMs/AudioSceneEnhancement.json

6. Profiles

No Profiles