Go to MPAI-MMC V2.5 AI Modules
Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance
1 Functions
The Access Control Registration (MMC‑ACR) AIM enrols a User for access control by face and speech. From the captured Face Object and Speech Object it produces the Face Descriptors and the Speech Descriptors of the User and records them, under the User Name, in the gallery of enrolled Users that Multimodal Access Control (MMC‑MAC) reads. A Portable Avatar confirms the enrolment aloud.
2 Reference Model
Figure 1 depicts the Reference Model of the Access Control Registration (MMC‑ACR) AIM.
Figure 1 – Reference Model of the Access Control Registration (MMC‑ACR) AIM
The operation of the Access Control Registration (MMC‑ACR) AIM develops in the following way:
- The human provides an image of the face and a speech sample, and types the User Name.
- The User Agent provides the Response to be spoken, the Personal Status of the avatar, the Avatar Model that represents the machine and the Machine ID.
- The machine records the Face Descriptors and the Speech Descriptors of the User under the User Name and provides the Portable Avatar that speaks the Response.
3 I/O Data
Table 1 specifies the Input and Output Data of the Access Control Registration (MMC‑ACR) AIM.
| Input | Description |
|---|---|
| Face Object | Image of the face of the User to be enrolled. |
| Speech Object | Speech of the User to be enrolled. |
| Personal Status | The Personal Status with which the avatar speaks. |
| Response | The Text the avatar speaks to confirm the enrolment (Port 1). |
| User Name | The name under which the User is enrolled, typed by the User (Port 2). |
| Avatar Model | The 3D model of the avatar that represents the machine. |
| Machine ID | Identifier of the machine. Optional. |
| Output | Description |
| Portable Avatar | The avatar that speaks the confirmation, with lip-synchronised Face Descriptors. |
4 SubAIMs
4.1 Reference Model
Figure 2 depicts the Reference Model of the Access Control Registration (MMC‑ACR) Composite AIM.
Figure 2 – Reference Model of the Access Control Registration (MMC‑ACR) Composite AIM
4.2 Operation
The Access Control Registration (MMC‑ACR) AIM receives the Face Object and the Speech Object of the User to be enrolled. Entity Face Description produces the Face Descriptors and Entity Speech Description produces the Speech Descriptors; both are recorded in the gallery of enrolled Users under the User Name. The gallery is Shared Storage, not a Port and not Access, which the AIMs of a Module only read: Multimodal Access Control reads it to recognise the User, together with the reference population of known people that Face Identity Recognition and Speaker Identity Recognition read from Access. Response and Scene Rendering speaks the Response and produces the lip-synchronised Machine Face Descriptors. The User Name is typed by the User. Acquisition and delivery are the User Agent’s, not SubAIMs.
4.3 Functions of SubAIMs
Table 2 provides the functions of the Access Control Registration (MMC‑ACR) SubAIMs.
| SubAIM | Function |
|---|---|
| Entity Face Description | Produces the Face Descriptors of the User from the Face Object and records them in the gallery under the User Name. |
| Entity Speech Description | Produces the Speech Descriptors of the User from the Speech Object and records them in the gallery under the User Name. |
| Response and Scene Rendering | Receives the Response, the Personal Status, the Avatar Model and the Machine ID and produces the Portable Avatar that speaks the Response with lip-synchronised Machine Face Descriptors. |
4.4 I/O Data of SubAIMs
Table 3 gives the Input and Output Data of the Access Control Registration (MMC‑ACR) SubAIMs.
| SubAIM | Input | Output |
|---|---|---|
| Entity Face Description | Face Object User Name |
Face Descriptors (gallery) |
| Entity Speech Description | Speech Object User Name |
Speech Descriptors (gallery) |
| Response and Scene Rendering | Response Personal Status Avatar Model Machine ID |
Portable Avatar |
4.5 AIMs and JSON Metadata
Table 4 provides the links to the AIM specifications and JSON schemas. AIM1 indicates the Composite AIM and AIM2 its SubAIMs.
| AIM1 | AIM2 | Name | JSON |
|---|---|---|---|
| MMC‑ACR | Access Control Registration | X | |
| PAF‑EFD | Entity Face Description | X | |
| MMC‑ESD | Entity Speech Description | X | |
| PAF‑RSR | Response and Scene Rendering | X |
5 JSON Metadata
https://schemas.mpai.community/MMC/V2.5/AIMs/AccessControlRegistration.json
6 Profiles
No Profiles.
7 Reference Software
Under development.
8 Conformance Testing
Table 5 provides the Conformance Testing Method for the Access Control Registration (MMC‑ACR) AIM. Conformance Testing of the individual SubAIMs is given by the individual AIM specifications.
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.
| Receives | Face Object | Shall validate against Basic Visual Object schema. Visual Data shall conform with Visual Qualifier. |
| Speech Object | Shall validate against Basic Speech Object schema. Speech Data shall conform with Speech Qualifier. | |
| Personal Status | Shall validate against Personal Status schema. | |
| Response | Shall validate against Basic Text Object schema. Text Data shall conform with Text Qualifier. | |
| User Name | Shall validate against Basic Text Object schema. Text Data shall conform with Text Qualifier. | |
| Avatar Model | Shall validate against Basic 3D Model Object schema. 3D Model Data shall conform with 3D Model Qualifier. | |
| Machine ID | Shall be a string. | |
| Produces | Portable Avatar | Shall validate against Portable Avatar schema. |
9 Performance Assessment
Not part of this specification.
