Abstract: A speech detection system is provided with multiple speech detector sub-systems. The speech detection sub-systems employ distinct statistical methods for determining whether speech is present in an electronic communication signal received at an output terminal. For example, a first speech detection sub-system employs moving average peak signal filter, a second speech detection sub-system employing a moving average noise filter, and a third speech detection sub-system employs a variance filter. Signals from each of the filters are compared with respective threshold values, and the threshold values are provided to speech determination logic for making an aggregate speech detection decision. The speech detection system is useful for telephonic automatic gain control.