-
Notifications
You must be signed in to change notification settings - Fork 17
Turn management based on VAP
sagatake edited this page Apr 4, 2025
·
9 revisions
Turn management module based on voice activity projection (VAP) model.
This module considers both of signals from the user and the agent.
Currently, there are two mode
- audio VAP
- audio and face embed VAP
Please follow common installation
- In Modular.jar, add Microphone module from [Add -> Input -> Microphone]
- In Modular.jar, add TurnManagement module from [Add -> Input -> Dialogue -> TurnManagement]
- Create the following connections in Modular.jar: Feedback -> TurnManagement, TurnManagement -> BehaviorPlanner
- When you are speaking something and Greta is not talking, the module randomly picks one XML file from bin/Examples/DemoEN/backchannel upon several rules written in /bin/Common/Data/TurnManagement/turnManager.py
- Some rules were based on the previous backchannels module
- For more details, please check the following sources
- Microphone java project at auxiliary/Microphone
- Python source code at bin/Common/Data/microphone
- 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