AUTOMATICALLY MONITORING FOR VOICE INPUT BASED ON CONTEXT

In one implementation, a computer-implemented method comprises: detecting a current context associated with a mobile computing device, the context being external to the mobile device and indicating current state of the device in its surrounding environment; determining, based on the current context indicating that monitoring audio data for voice input will have at least a threshold level of convenience for a user associated with the mobile computing device, whether to switch the mobile computing device from a current mode of operation to a second mode of operation during which the mobile computing device monitors ambient sounds for voice input that indicates a request to perform an operation; in response to determining whether to switch to the second mode of operation, activating one or more microphones and/or a speech analysis subsystem associated with the mobile computing device so that the mobile computing device receives a stream of audio data; and providing output on the mobile computing device that is responsive to voice input that is detected in the stream of audio data and that indicates a request to perform an operation.