I am developing a game in Unity that plays human speech through speakers and also performs speech recognition. This will cause the sound played by the speakers to be recognized by the speech recognition, which will lead to inaccurate speech recognition results or even the inability to recognize the correct speech.
I'm using whisper.unity for speech recognition.
What are some possible solutions to this problem?
I have only learned about "echo cancellation" through Google search, but I still don't know how to handle it.