Methods and apparatus for detecting a voice command

1 . A method for detecting a voice command by a mobile device having a plurality of processors and a plurality of microphones, the method comprising:

receiving, via a first microphone, an acoustic input while a primary processor and a second microphone are inactive and a secondary processor is active;

processing, via the secondary processor, the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity;

responsive to the acoustic input not relating the spurious acoustic activity, activating the primary processor; and

processing, via the primary processor, the acoustic input to detect a voice command based on at least one contextual cue without using a trigger word.

2 . The method of claim 1 , further comprising: activating the second microphone while the primary processor is inactive in response to the acoustic input exceeding a threshold.

3 . The method of claim 2 , wherein the threshold includes at least one of a volume amplitude, a time duration, or an acoustic energy.

4 . The method of claim 1 , further comprising: activating the second microphone in response to detecting the voice command in the acoustic input.

5 . The method of claim 1 , further comprising: processing, via the primary processor, the acoustic input to detect a voice command based on at least one of a volume of the acoustic input, or an energy of the acoustic input.

6 . The method of claim 1 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.

7 . The method of claim 1 , wherein the spurious acoustic activity includes a speech not corresponding to any voice command.

8 . The method of claim 1 , wherein the at least one contextual cue includes at least one of: time of day, motion of the device, location of the device, an occurrence of an event on the device, recent activity on the device, and state of a battery powering the device.

9 . A mobile device, comprising:

a first microphone;

a second microphone;

a primary processor; and

a secondary processor programmed to:

responsive to receiving, via a first microphone, an acoustic input while a primary processor and a second microphone are inactive, compare the acoustic input with a threshold, and responsive to detecting the acoustic input exceeds the threshold, instruct the second microphone to activate while the primary processor is still inactive,

wherein the primary processor is programmed to:

detect a voice command in the acoustic input based on at least one contextual cue without using a trigger word.

10 . The mobile device of claim 9 , wherein the secondary processor is further programmed to:

process the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity; and

responsive to the acoustic input not relating the spurious acoustic activity, instructing the primary processor to activate.

11 . The mobile device of claim 10 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.

12 . The mobile device of claim 10 , wherein the spurious acoustic activity includes a speech not corresponding to any voice command.

13 . The mobile device of claim 9 , wherein the threshold includes at least one of a volume amplitude, a time duration, or an acoustic energy.

14 . The mobile device of claim 9 , wherein the secondary processor is further programmed to: activate the second microphone response to detecting the voice command in the acoustic input.

15 . The mobile device of claim 9 , wherein the primary processor is programmed to: detect a voice command in the acoustic input based on at least one of a volume of the acoustic input, or an energy of the acoustic input.

16 . A non-transitory computer readable medium encoded with instructions that, when executed on at least one processor, perform a method of monitoring an acoustic environment of a mobile device to receive acoustic input in multiple stages including in a low power stage and normal power stage, the method comprising:

receiving, via a first microphone, an acoustic input in the low power stage while a primary processor and a second microphone are inactive and a secondary processor is active;

processing, in the lower power stage, the acoustic input to determine whether the acoustic input relates to a spurious acoustic activity;

responsive to the acoustic input not relating the spurious acoustic activity, activating the primary processor to enter into the normal power stage; and

processing, in the normal power stage, the acoustic input to detect a voice command based on at least one contextual cue without using a trigger word.

17 . The non-transitory computer readable medium of claim 16 , wherein the method further comprising:

activating the second microphone, in the low power stage, in response to the acoustic input exceeding a threshold.

18 . The non-transitory computer readable medium of claim 17 , wherein the threshold includes a volume amplitude and a time duration.

19 . The non-transitory computer readable medium of claim 16 , wherein the method further comprising:

activating the second microphone response to detecting the voice command in the acoustic input.

20 . The non-transitory computer readable medium of claim 16 , wherein the spurious acoustic activity includes a speech uttered by a non-recognized user voice.