Project is still in it's development stage. Project is being done by a group of five Undergraduates of University of Moratuwa.
In this section we are experimenting, how we can retrieve the spatial sounds in a virtual world using a stero sound output. We are using Unity
game development platform for experiments. You can run simulation by yourself.
Unity
2021.1.12f1 or higher versionVisual Studio 2019
or higher version
- Clone the repository,
- Open the file
/spatial-sound-system-development/Assets/testfield.unity
in Unity, - Run the simulation,
- You can use mouse and keyboard to move around the virtual world,
- You also can edit the
C#
script and experiment.
In here we have developed two models, namely the text-to-speech model and the speech-to-text model.
We have developed an offline model to convert a given list of names into voice.
python 3.8
numpy
pyttsx3
This model works in online state and will convert the given voice commands into text.
python 3.8
numpy
speech_recognition
pyaudio