CPC G10L 15/22 (2013.01) [G06F 3/013 (2013.01); G10L 15/14 (2013.01); G10L 15/25 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01); G10L 2015/227 (2013.01)] | 14 Claims |
1. A method of presenting a signal to a speech processing engine, the method comprising:
receiving, via a first microphone of a wearable head device, an audio signal comprising speech from a user of the wearable head device;
identifying a first portion of the audio signal;
determining, for the first portion of the audio signal, a first probability that the first portion comprises speech directed by a user as input to the speech processing engine;
identifying a second portion of the audio signal, the second portion subsequent to the first portion in the audio signal;
determining, for the second portion of the audio signal, a second probability that the second portion comprises speech directed by the user as input to the speech processing engine;
identifying a third portion of the audio signal, the third portion subsequent to the second portion in the audio signal;
determining, for the third portion of the audio signal, a third probability that the third portion comprises speech directed by the user as input to the speech processing engine; and
in accordance with a determination that the first probability exceeds a first threshold, further in accordance with a determination that the second probability does not exceed the first threshold, and further in accordance with a determination that the third probability exceeds the first threshold:
presenting the first portion of the audio signal and the third portion of the audio signal as a first input to the speech processing engine, wherein the first input does not include the second portion of the audio signal.
|