1     Functions

TV Diarisation (MMC-TVD) separates mixed speech in its component Speech Objects.

2      Reference Architecture

Figure 1 depicts the Reference Architecture of the MMC-TVD.

Figure 1 – MMC-TVDReference Model

3      I/O Data

Table 1 specifies the Input and Output Data of MMC-TVD.

Table 1 – I/O Data of MMC-TVD

Input Description
Speech Object Speech Object emitted by Entity.
Time Time stamp related to the Speech Object.
Output Description
Recognised Text Output of the Automatic Speech Recognition AIM
Time Time stamp related to Recognised Text,

4      SubAIMs

No SubAIMs.

5      Profiles

No Profiles

6     JSON Metadata