← Registry / Multimodal Conversation
AIM · composite
Multimodal Translation Service
MMC-MTS-V2.5
Submissions for this AIM must match this definition: the same ports, API profile and internal wiring.
Description
Multimodal Translation Service: the HCI Module for spoken translation with a Portable Avatar. Automatic Speech Recognition recognises the human's speech into text; Text-to-Text Translation translates it into the language named by the Language Selector; Text-To-Speech makes the Speech Object of the translation; Portable Avatar Multiplexing puts the translation, text and speech, in the Portable Avatar, which the User Agent renders. The translated text is also exposed. Non-affective; no Personal Status is supplied. Acquisition and delivery are the User Agent, not sub-AIMs.
Inputs and outputs 5 in · 2 out
Inputs
- InputSpeech optional OSD-BSO-V1.5
- TargetLanguage OSD-SEL-V1.5
- TextToTranslate optional OSD-BTO-V1.5
- AvatarModel OSD-B3O-V1.5
- MachineID optional string
Outputs
- TranslatedText OSD-BTO-V1.5
- PortableAvatar PAF-PAV-V1.6
Built from 4 AIMs
| AIM | Code | Instances |
|---|---|---|
| Automatic Speech Recognition | MMC-ASR-V2.5 | 1 |
| Text to Text Translation | MMC-TTT-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.