1      Version


2     Functions

Human and Machine Communication (MPAI-HMC) – enables a human or a “Machine” (that is, an Implementation that receives, processes, and produces Data having a Format specified by MPAI-HMC) to communicate with:

  1. A real human, either in a real space or represented as a Digitised Human in a Virtual Space, or
  2. A Machine, displayed as a speaking humanoid in the real space, represented as a speaking Virtual Human in a Virtual Space, or running as a process, or
  3. An “Entity” (i.e., human or Machine), reached through a Machine acting as an interpreter between the cultural environments of the source and the destination Entity.

2      Reference Architecture

Figure 9 depicts the HMC-SID Reference Architecture.

Figure – The Human and Machine Communication (MPAI-HMC) AIW

4      I/O Data

The Input and Output Data of Human and Machine Communication are specified in the Table.

Table – I/O Data of the Human and Machine Communication AIW

Input Description
Portable Avatar A Communication Item emitted by the Machine.
Input Selector Selector containing data that determines:

1.     Whether an Entity uses Speech or Text an input.

2.     Which language is used as input.

3.     The target Language in translation.

Input Text Text Object generated by Entity as information additional to or in lieu of Speech Object.
Input Audio The audio scene captured by the Machine.
Input Visual The visual scene captured by the Machine.
Output Description
Portable Avatar The Communication Item produced by the Machine.
Output Text The Text in the Communication Item.
Output Audio The rendered audio corresponding to the Audio in the Communication Item.
Output Visual The rendered visual corresponding to the visual in the Communication Item.

5      SubAIMs

  1. AV Scene Integration & Description (HMC-SID)
  2. Audio-Visual Scene Description (OSD-AVD)
  3. Entity Context Understanding (MMC-ECU)
  4. Entity Dialogue Processing (MMC-EDP)
  5. Personal Status Display (PAF-PSD)
  6. Audio-Visual Scene Rendering (PAF-AVR).

6     JSON Metadata