How to simultaneously run Android speech to text and another activity which uses camera

Question

I am new to Android and am trying to develop an application which would capture the speaker's facial expressions via camera and simultaneously convert speech to text. I am using Affectiva's affdex API for real time facial emotions recognition. Whenever I try to launch the speech to text module via a button, the facial recognition stops, the STT modules completes and then the facial recognition module restarts. I want to have them work simultaneously.