MPAI-MMC V2.2 AIMs Speaker Identity Recognition

1. Functions

Speaker Identity Recognition (MMC-SIR):

Receives	Auxiliary Text related to the Speech Object.
	Speech Object of which the Speaker id requested.
	Speech Time for which a Speaker ID is requested.
Produces	Speaker Identifier

2      Reference Architecture

The Reference Architecture is depicted in Figure 1.

Figure 1 – The Speaker Identity Recognition AIM

3      I/O Data

Table 1 specifies the Input and Output Data of the Visual Scene Description AIM.

Table 1 – I/O Data of the Visual Scene Description AIM

Input	Description
Auxiliary Text	Text with content related to Speaker ID.
Speech Object	Speech Object emitted by the Speaker.
Speech Time	The start and end time of the Speech
Speech Overlap	Number of speakers
Output	Description
Speaker Identifier	The Visual Descriptors of the Visual Scene.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.2/AIMs/SpeakerIdentityRecognition.json

5     SubAIMs

No SubAIMs

6. Profiles

No Profiles