Improve Accuracy Speech Recognition

[Priyank_T_]

How can we improve accuracy in speech recognition. Currently i am using Commands and Dictionary. Are there any more ways to improve this further. Can we create an audio dictionary as well such  that a particular audio should be recognized as a particular sentence,

   PXCMSpeechRecognition sr;
            session.CreateImpl<PXCMSpeechRecognition>(out sr);
                   // sr is a PXCMSpeechRecognition instance.

            String[] cmds = new String[9] { "Switch on",  
                  "Light Off",
                 "Up",
                 "Down",
                 "Raise",
                 "Two",
                 "Three",
                 "Four",
                 "Five"
              };

            // Build the grammar.
            sr.BuildGrammarFromStringList(1, cmds, null);
      
            // Set the active grammar.
            sr.SetGrammar(1);

[MartyG]

Slightly off topic but I remember the "fun" I had with speech recognition when using the 2013 Intel Perceptual Computing SDK (the one before RealSense).  I spent five hours testing the speech by constantly saying "Woo hoo" to the camera to see if it successfully converted the speech to text.  The results were mixed, as it possibly struggled with my British accent.  Moreover, I drove the people around me crazy with my repetition  :)