← Registry / Multimodal Conversation
AIM
Automatic Speech Recognition
MMC-ASR-V2.5
Submissions for this AIM must match this definition: the same ports, API profile and internal wiring.
Description
Automatic Speech Recognition: receives an Audio Object and provides a Text Object and Speech Descriptors.
Inputs and outputs 6 in · 3 out
Inputs
- LanguageSelector optional OSD-SEL-V1.5
- AuxiliaryText optional OSD-TXO-V1.5
- SpeakerID optional OSD-IID-V1.5
- SpeechOverlap optional MMC-SOL-V2.5
- ImageSpeech optional OSD-BSO-V1.5
- ResponseSpeech optional OSD-BSO-V1.5
Outputs
- RecognisedText OSD-BTO-V1.5 or OSD-TXO-V1.5
- SpeechDescriptors optional MMC-SDO-V2.5
- TextQuestion OSD-BTO-V1.5
Used in 4 AIMs
- Affective Multimodal Conversation MMC-AMC-V2.5
- Answer to Multimodal Question MMC-AMQ-V2.5
- Multimodal Conversation Avatar MMC-MCA-V2.5
- Multimodal Translation Service MMC-MTS-V2.5
Documentation
Implementations 0
None published yet.