Go To MPAI-OSD AI Modules

1     Function 2     Reference Model 3     Input/Output Data
4     SubAIMs 5     JSON Metadata 6     Profiles
7     Reference Software 8     Conformance Texting 9     Performance Assessment

1     Functions

Audio-Visual Scene Demultiplexing (OSD-SDX):

Receives Audio-Visual Scene Descriptors
Demultiplexes Audio-Visual Scene Descriptors
Produces Speech Scene Geometry
Audio Scene Geometry
Visual Scene Geometry
Speech Objects
Audio Objects
Visual Objects

2     Reference Model

Figure 1 depicts the Reference Model of the Audio-Visual Scene Demultiplexing AIM.

Figure 1 – Audio-Visual Scene Demultiplexing

3    Input/Output Data

Table 1 specifies the Input and Output Data of the of the Audio-Visual Scene Demultiplexing AIM.

Table 1 – I/O Data of the Audio-Visual Scene Demultiplexing AIM

Input Description
Audio-Visual Scene Descriptors The Descriptors of the Audio-Visual Scene.
Output Description
Space-Time Space-Time information of the Audio-Visual Scene
Speech Scene Geometry The Descriptors of the Speech Scene.
Audio Scene Geometry The Descriptors of the Audio Scene.
Visual Scene Geometry The Descriptors of the Visual Scene.
Audio Object The Audio Objects in the Scene.
Speech Object The Speech Objects in the Scene.
Visual Object The Visual Objects in the Scene.

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/OSD/V1.1/AIMs/AudioVisualSceneDemultiplexing.json

6     Profiles

No Profiles.

7     Reference Software

8     Conformance Testing

9     Performance Assessment

Go To MPAI-OSD AI Modules