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 Avatar and Speech Rendering (PAF-ASR) AIM produces the Visual Object corresponding to an avatar synthesised from an Avatar Module animated by Face and Body Descriptors and the Speech Object from input Face Descriptors, input Body Descriptors, input Avatar Model, and input Speech (which is rendered unchanged as Output Speech).
Receives | Input Speech | Speech uttered by the avatar. |
Face Descriptors | Avatar Face Descriptors. | |
Body Descriptors | Avatar Body Descriptors. | |
Avatar Model | When a specific Avatar Model is externally provided. | |
Produces | Output Speech | The input Speech Object . |
Output Visual | The rendering of the animated avatar. |
2 Reference Model
Figure 1depicts the Reference Model of the Avatar and Speech Rendering (PAF-ASR) AIM.
Figure 1– The Avatar and Speech Rendering (PAF-ASR) AIM
3 Input/Output Data
Table 1 specifies the Input and Output Data of the Avatar and Speech Rendering (PAF-ASR) AIM.
Table 1– I/O Data of the Avatar and Speech Rendering (PAF-ASR) AIM
Input | Description |
Input Speech | Speech uttered by the avatar. |
Face Descriptors Object | Avatar Face Descriptors. |
Body Descriptors Object | Avatar Body Descriptors. |
Avatar Model | To be animated. |
Output | Description |
Output Speech | Speech from input. |
Output Visual | Rendering of animated avatar. |
4 SubAIMs
No SubAIMs.
5 JSON Metadata
https://schemas.mpai.community/PAF/V1.5/AIMs/AvatarAnimationAndSpeech.json
6 Profiles
No Profiles
7 Reference Software
8 Conformance Testing
Table 2 provides the Conformance Testing Method for the Avatar and Speech Rendering (PAF-ASR) 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 Avatar and Speech Rendering (PAF-ASR) AIM
Input | Description |
Input Speech | Shall validate against Speech Object Schema. |
Face Descriptors Object | Shall validate against Face Descriptors Schema. |
Body Descriptors Object | Shall validate against Body Descriptors Schema. |
Avatar Model | Shall validate against 3D Model Object Schema. |
Output | Description |
Output Speech | Shall validate against Speech Object Schema. |
Output Visual | Shall validate against Visual Object Schema. |