Go To MPAI-PAF 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

Portable Avatar Demultiplexing (PAF-PDX):

Receives Portable Avatar
Demultiplexes Elements in Portable Avatar.
Produces – Portable Avatar ID
– Avatar Space-Time
– Avatar
– Language Selection
– Speech Object
– Text Object
– Speech Model
– Personal Status
– Audio Visual Scene Descriptors
– Audio Visual Scene Space Time

2     Reference Model

Figure  1 specifies the Reference Model of the Personal Avatar Demultiplexing (PAF-PDX) AIM.

Figure  1– The Personal Avatar Demultiplexing (PAF-PDX) AIM

3    Input/Output Data

Table 1 specifies the Input and Output Data of the Portable Avatar Demultiplexing (PAF-PDX) AIM.

Table 1 – Portable Avatar Demultiplexing (PAF-PDX) AIM

Input Description
Portable Avatar From an upstream AIM or another AIW.
Output Description
AvatarID Avatar ID.
Avatar Space-Time Portable Avatar Time.
Avatar Avatar in Portable Avatar.
Language Selector Language of Avatar.
Speech Object The Speech in the time when the PA is valid.
Text Object The Time in the time when the PA is valid.
Speech Model The NN Model used to synthesise text.
Avatar Personal Status The Avatar’s Personal Status.
AV Scene Descriptors  Descriptors of AV Scene.
AV Scene Space-Time  Space-Time info of AV Scene.

4     SubAIMs

No SubAIMs.

5     JSON Metadata

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

6     Profiles

No Profiles.

7     Reference Software

8     Conformance Testing

9     Performance Assessment

Go To MPAI-PAF AI Modules