MPAI-PAF V1.2 AIMs Audio Scene Creation

1     Functions

Audio Scene Creation (PAF-ASC):

Receives	Avatar ID
	Audio-Visual Scene Descriptors
	Avatar Model
	Spatial Attitude
	Body Descriptors
	Face Descriptors
Produces	Visual Scene Descriptors
	Spatial Attitude of Avatars’ Mouths

2     Reference Architecture

Figure 1depicts the Reference Architecture of the Audio Scene Creation (PAF-ASC) AIM.

 

Figure 1– The Audio Scene Creation (PAF-ASC) AIM

3     I/O Data

Table 1specifies the Input and Output Data of the  Audio Scene Creation (PAF-ASC) AIM.

Table 1– I/O Data of the Audio Scene Creation (PAF-ASC) AIM

Input	Description
Avatar IDs	IDs of Participants’ and MVS’ Avatars
Audio-Visual Scene Descriptors	Descriptors of the Initial Visual Scene
Avatar Models	Models of Participants’ and VMS’ Avatars
Spatial Attitudes	Spatial Attitudes of Participants’ and VMS’ Avatars
Body Descriptors	Body Descriptors of Participants’ and VMS’ Avatars
Face Descriptors	Face Descriptors of Participants’ and VMS’ Avatars
Speech Objects	Speech Objects of Participants’ and VMS’ Avatars
Text Objects	Text Objects of Participants’ and VMS’ Avatars
Output	Description
Visual Scene Descriptors	Descriptors of the entire Visual Scene
Mouth Spatial Attitudes	The Spatial Attitudes of the Mouths of Participants’ and VMS’ Avatars

4     SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/PAF/V1.2/AIMs/AudioSceneCreation.json

6     Profiles

No Profiles