-
Notifications
You must be signed in to change notification settings - Fork 17
Watson
sagatake edited this page Apr 10, 2025
·
1 revision
Watson: uses the same methods as OSC_Sender. It receives text from Unity, so that it can take it as input and generate multimodal behavior. In the interface, the WATSON module is put in place of the FMLReader
ExampleTextToSpeech: takes care of the communication with IBMWatson, using the parameters of the assistant created directly on the IBM website. In these modules you have to insert the keys, url necessary to establish the communication with the chatbot. Then there are two InputTextFields:
- in the first one the chatbot will mark its answers which will then be sent automatically to the Watson module in GRETA
- in the other one at the bottom you write text to communicate with the chatbot
- Generating New Facial expressions
- Generating New Gestures
- Generating new Hand configurations
- Creating an Instance for Interaction
- Create a new virtual character
- Creating a Greta Module in Java
- Integration examples
- Development guideline
- Naming policy
- Github repository
- Technical showcase
- Python integration
- Known issues
- Technical Specifications
- Pitfalls for Greta development
-
FML/BML
-
Tools
-
AUs from external sources
-
Large language model (LLM)
-
Automatic speech recognition (ASR)
-
Extensions
Nothing to show :)
- Incrementality
- Motion Capture to BAP values
- Interruptions
- Back Channels
- Appreciation Generator
- SSI Greta Integration
- TopicPlanner
- Shore
- Disco
- Watson
- Object node controller
- OSC communication for Unity
- 3D pose estimation from RGB camera through VAE (PFE-OpenPose-to-VAE-to-BVH)
- HOW TO CREATE BEHAVIOR SET
- Projects
- Signals