← Registry / Multimodal Conversation
AIM · composite
Answer to Multimodal Question
MMC-AMQ-V2.5
Submissions for this AIM must match this definition: the same ports, API profile and internal wiring.
Description
Answer to Multimodal Question: receives a Visual Object and a question - as a Speech Object or a Text Object - and returns the answer as a Portable Avatar, which utters it, and the Visual Object. Automatic Speech Recognition recognises the spoken question; Text and Image Query answers the question about the image; Text-To-Speech makes the Speech Object of the answer; Portable Avatar Multiplexing puts the answer, text and speech, in the Portable Avatar, which the User Agent renders.
Inputs and outputs 4 in · 2 out
Inputs
- InputVisual OSD-BVO-V1.5
- InputSpeech optional OSD-BSO-V1.5
- InputText optional OSD-BTO-V1.5
- MachineID string
Outputs
- OutputVisual OSD-BVO-V1.5
- PortableAvatar PAF-PAV-V1.6
Built from 4 AIMs
| AIM | Code | Instances |
|---|---|---|
| Automatic Speech Recognition | MMC-ASR-V2.5 | 1 |
| Text and Image Query | MMC-TIQ-V2.5 | 1 |
| Text to Speech | MMC-TTS-V2.5 | 1 |
| Portable Avatar Multiplexing | PAF-PMX-V1.6 | 1 |
Documentation
Implementations 0
None published yet.