← Registry / Multimodal Conversation
AIM · composite
Multimodal Conversation Avatar
MMC-MCA-V2.5
Submissions for this AIM must match this definition: the same ports, API profile and internal wiring.
Description
Multimodal Conversation Avatar: the HCI Module for anonymous dialogue with a Portable Avatar (no identity, no Identity Reconciliation, no Personal Status). Automatic Speech Recognition recognises the human's speech into text, or the human types it; Entity Dialogue Processing produces the machine's response Text (the Summary of the conversation is internal to it); Text-to-Speech gives the response its Machine Speech, Generative Face Description the lip-synced Machine Face Descriptors, and Portable Avatar Multiplexing combines Speech, Text, Face Descriptors, Avatar Model and Machine ID into the Portable Avatar.
Inputs and outputs 5 in · 2 out
Inputs
- InputSpeech optional OSD-BSO-V1.5
- InputText optional OSD-BTO-V1.5
- AvatarModel OSD-B3O-V1.5
- MachineID optional string
- Summary optional MMC-SUM-V2.5
Outputs
- PortableAvatar PAF-PAV-V1.6
- EditedSummary MMC-SUM-V2.5
Built from 5 AIMs
| AIM | Code | Instances |
|---|---|---|
| Automatic Speech Recognition | MMC-ASR-V2.5 | 1 |
| Entity Dialogue Processing | MMC-EDP-V2.5 | 1 |
| Text to Speech | MMC-TTS-V2.5 | 1 |
| Generative Face Description | PAF-GFD-V1.6 | 1 |
| Portable Avatar Multiplexing | PAF-PMX-V1.6 | 1 |
Documentation
Implementations 0
None published yet.