1     Version

V1.1

2    Functions

Visual Scene Creation (PAF-VSC):

  1. Receives
    1. Mouth Spatial Attitudes
    2. Avatar ID
    3. Input Speech
  2. Attaches Input Speech to the Avatar’s mouth.
  3. Produces Audio Scene Descriptors.

3      Reference Model

The Reference Model is depicted in Figure 1.

Figure 1 – The Audio Scene Creation AIM

4      I/O Data

Table 1 specifies the Input and Output Data of the .

Table 1 – I/O Data of the Service Participant Authentication AIM

Input Description
Mouth Spatial Attitude Spatial Attitude of the Avatar’s mouth..
Avatar ID ID of the Avatar (string)..
Input Speech Participant’s Speech.
Outputs Description
Audio Scene Descriptors Visual meeting space at the Client Receiver.

5     JSON Metadata

https://schemas.mpai.community/PAF/V1.1/AIMs/AudioSceneCreation.json

6     SubAIMs

No SubAIMs