Adjust Background noice sensitivity in Android Speech-to-text recognition

Question

Android Speech-to-text is very sensitive to background noises. The use-case is to use Speech-to-text in an area where light background noises will be constant. Want to control the speech recognition only with certain voice levels.

Tried working around using RMS and Buffer input from Speech Recogniser. Some workaround using same logic would be helpful.

Callbacks returned from Android Speech-to-text recogniser are :

override fun onReadyForSpeech(params: Bundle?) {
    }
override fun onRmsChanged(rmsdB: Float) {
    }
override fun onBufferReceived(buffer: ByteArray?) {
    }
override fun onEvent(eventType: Int, params: Bundle?) {
    }
override fun onBeginningOfSpeech() {
    }
override fun onEndOfSpeech() {
    }
override fun onError(error: Int) {
    }
override fun onPartialResults(partialResults: Bundle?){
    }
override fun onResults(results: Bundle?) {
    }