MPAI-PAF V1.6 AIMs Portable Avatar Multiplexing

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

The Portable Avatar Multiplexing (PAF-PMX) AIM Multiplexes the input component elements of a Portable Avatar – Portable Avatar ID, Avatar Space-Time, Avatar, Language Selector, Speech Object, Text Object, Face Descriptors, Body Descriptors, Speech Model, Personal Status, Audio-Visual Scene Descriptors, Audio-Visual Scene Space Time, and Avatar Spatial Attitude into a Portable Avatar:

Receives	An arbitrary number of elements in Portable Avatar out of:
	– Portable Avatar ID
	– Avatar Space-Time
	– Avatar
	– Language Selector
	– Text Object
	– Face Descriptors
	– Body Descriptors
	– Speech Model
	– Speech Object
	– Personal Status
	– Audio- Visual Scene Space-Time
	– Audio-Visual Scene Descriptors
	– Avatar Spatial Attitude
	– An existing Portable Avatar
Changes	Existing with Input Data
Adds	Input Data that is not in the Input Portable Avatar
Produces	Portable Avatar

Only the Speech Object is required; every other element is taken where it is given.

2 Reference Model

Figure 1 specifies the Reference Model of the Portable Avatar Multiplexing (PAF-PMX) AIM.

Figure 1 – The Portable Avatar Multiplexing (PAF-PMX) AIM

3 Input/Output Data

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

Table 1 – I/O Data of the Portable Avatar Multiplexing (PAF-PMX) AIM

Input	Description
AvatarID	Avatar ID.
Avatar Space-Time	Portable Avatar Time.
Avatar	The Avatar Model, represented by a Basic 3D Model Object, of the Portable Avatar.
Language Selector	Language of Avatar.
Speech Object	The Speech in the time when the PA is valid.
Text Object	The Text 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.
Face Descriptors Object	Descriptive (of a participant) or generative (of a machine) Face Descriptors.
Body Descriptors Object	Descriptive or generative Body Descriptors.
Avatar Spatial Attitude	Spatial Attitude of the Avatar in the Audio-Visual Scene.
Portable Avatar	The input Portable Item.
Output	Description
Portable Avatar	The output Portable Item.

4 SubAIMs

No SubAIMs.

5 JSON Metadata

https://schemas.mpai.community/PAF/V1.6/AIMs/PortableAvatarMultiplexing.json

6 Profiles

No Profiles.

7 Reference Software

8 Conformance Testing

Table 2 provides the Conformance Testing Method for PAF-PMX AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for PAF-PMX AIM

Receives	AvatarID	Shall be string or validate against Instance ID Schema
	Avatar Space-Time	Shall validate against Space-Time Schema
	Avatar	Shall validate against Basic 3D Model Object schema.
	Language Selector	Shall validate against Selector Schema
	Speech Object	Shall validate against Speech Object Schema. Text Data shall conform with SpeechQualifier.
	Text Object	Shall validate against Text Object Schema. Speech Data shall conform with Text Qualifier.
	Speech Model	Shall validate against Machine Learning Model Schema. Speech Model Data shall conform with Machine Learning Model Qualifier.
	Avatar Personal Status	Shall validate against Personal Status Schema.
	AV Scene Descriptors	Shall validate against AV Scene Descriptors Schema.
	AV Scene Space-Time	Shall validate against Space-Time Schema.
	Avatar Spatial Attitude	Shall validate against Spatial Attitude Schema.
Produces	Portable Avatar	Shall validate against Portable Avatar Schema. Portable Avatar Data shall conform with respective Qualifiers.

9 Performance Assessment

Go To MPAI-PAF AI Modules