Go to MPAI-OSD V1.5 AI Modules
Function
Ref. Model
I/O Data
SubAIMs
JSON MData
Profiles
Ref. Software
Conformance
Performance
1 Functions
The User Identification (OSD-UID) AIM identifies a user from the face and the speech and reconciles the two into one answer. Speaker Identity Recognition matches the speech, Face Identity Recognition matches the face, and Identity Reconciliation combines the two identities. Identification states whether the face and the speech match somebody known; User ID states who.
| Receives | User Speech | The speech of the user. |
| Speech Scene Descriptors | The Descriptors of the speech scene. | |
| User Face | The face of the user. | |
| Visual Scene Descriptors | The Descriptors of the visual scene. | |
| Produces | Identification | True when the face and the speech match somebody known. |
| User ID | Who the user is. |
2 Reference Model
Figure 1 depicts the Reference Model of the User Identification (OSD-UID) AIM.
Figure 1 – Reference Model of the User Identification (OSD-UID) AIM
3 I/O Data
Table 1 specifies the Input and Output Data of the User Identification (OSD-UID) AIM. Links are to the Data Type specifications.
| Input | Data Type | Description |
|---|---|---|
| User Speech | Basic Speech Object (optional) | The speech of the user. |
| Speech Scene Descriptors | Basic Audio Scene Descriptors (optional) | The Descriptors of the speech scene. |
| User Face | Basic Visual Object (optional) | The face of the user. |
| Visual Scene Descriptors | Basic Visual Scene Descriptors (optional) | The Descriptors of the visual scene. |
| Output | Data Type | Description |
| Identification | boolean | True when the face and the speech match somebody known. |
| User ID | Instance Identifier (optional) | Who the user is. |
4 SubAIMs
Table 2 lists the SubAIMs of the User Identification (OSD-UID) AIM.
| SubAIM | Acronym | Function |
| Speaker Identity Recognition | MMC-SIR | Matches the speech of the user and produces the Speaker ID. |
| Face Identity Recognition | PAF-FIR | Matches the face of the user and produces the Face ID. |
| Identity Reconciliation | OSD-IDR | Reconciles the Face ID and the Speaker ID into the User ID and the Identification. |
5 JSON Metadata
https://schemas.mpai.community/OSD/V1.5/AIMs/UserIdentification.json
6 Profiles
No Profiles.
7 Reference Software
Not part of this specification.
8 Conformance Testing
Table 3 provides the Conformance Testing Method for the OSD-UID 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.
| Receives | User Speech (Basic Speech Object) | Shall validate against the Basic Speech Object schema. |
| Speech Scene Descriptors (Basic Audio Scene Descriptors) | Shall validate against the Basic Audio Scene Descriptors schema. | |
| User Face (Basic Visual Object) | Shall validate against the Basic Visual Object schema. | |
| Visual Scene Descriptors (Basic Visual Scene Descriptors) | Shall validate against the Basic Visual Scene Descriptors schema. | |
| Produces | Identification | Shall be a boolean. |
| User ID (Instance Identifier) | Shall validate against the Instance Identifier schema. |
9 Performance Assessment
Not part of this specification.
