Methods and apparatus for detecting a voice command

1. A method of monitoring an acoustic environment of a mobile device, the method comprising:

receiving, by the mobile device, acoustic input from the environment of the mobile device while the mobile device is operating in a low power mode;

detecting whether the acoustic input includes a voice command from a user without requiring receipt of an explicit trigger from the user; and

initiating responding to the detected voice command.

2. The method of claim 1 , wherein detecting whether the acoustic input includes a voice command from the user comprises performing a plurality of processing stages on the acoustic input to evaluate whether the acoustic input includes the voice command or corresponds to spurious acoustic activity.

3. The method of claim 2 , wherein performing at least one of the plurality of processing stages provides an indication of confidence that the acoustic input includes a voice command, the method further comprising selecting a subsequent processing stage to next process the acoustic input based, at least in part, on the indication of confidence from the at least one of the plurality of processing stages.

4. The method of claim 2 , further comprising:

discontinuing further processing of the acoustic input if a given processing stage of the plurality of processing stages determines that the acoustic input resulted from spurious acoustic activity;

initiating responding to the voice command if the given processing stage determines that the acoustic input includes a voice command; and

processing the acoustic input in a subsequent processing stage selected from the plurality of processing stages if the given processing stage cannot conclude whether the acoustic input includes a voice command.

5. The method of claim 2 , wherein performing the plurality of processing stages includes performing at least one voice activity detection processing stage.

6. The method of claim 5 , wherein performing the at least one voice activity detection processing stage comprises performing spectral analysis on the acoustic input to evaluate whether a spectrum of the acoustic input is indicative of voice activity.

7. The method of claim 5 , wherein performing the at least one voice activity detection processing stage comprises performing periodicity analysis to evaluate whether signal periodicity of the acoustic input is indicative of voice activity.

8. The method of claim 5 , wherein performing the at least one voice activity detection processing stage comprises using phone loops to evaluate whether the acoustic input includes speech.

9. The method of claim 2 , wherein performing at least one of the plurality of processing stages comprises performing at least one biometric analysis on the acoustic input to evaluate whether the acoustic input was received from the user of the mobile device.

10. The method of claim 9 , wherein performing the at least one speech processing stage includes performing at least one natural language processing stage.

11. The method of claim 2 , wherein performing the plurality of processing stages comprises performing at least one speech processing stage.

12. The method of claim 11 , wherein performing the at least one speech processing stage comprises performing limited vocabulary automatic speech recognition on the acoustic input.

13. The method of claim 11 , wherein performing the at least one speech processing stage comprises performing classification of the acoustic input including applying one or more statistical classifiers to evaluate whether the recognized speech is characteristic of a voice command.

14. The method of claim 2 , wherein the mobile device is coupled to a plurality of microphones and wherein the mobile device stores a first direction computed using signals received from the plurality of microphones, the first direction indicating a direction from which speech from the user of the mobile device was received, and wherein performing at least one of the plurality of processing stages comprises:

determining a second direction from which the acoustic input is received; and

comparing the first direction and the second direction to evaluate the likelihood the acoustic input was received from the user.

15. The method of claim 2 , wherein the mobile device includes a primary processor and a secondary processor, and wherein at least one first processing stage of the plurality of processing stages is performed by the secondary processor prior to engaging the primary processor to process the acoustic input.

16. The method of claim 15 , wherein at least one second processing stage of the plurality of processing stages is performed by the primary processor only after the at least one first processing stage neither concludes that the acoustic input includes a voice command nor concludes that the acoustic input is the result of spurious acoustic activity.

17. The method of claim 2 , wherein performing at least one of the plurality of processing stages comprises evaluating at least one contextual cue selected from a group consisting of: time of day, motion of the mobile device, location of the mobile device, an occurrence of an event on the mobile device, recent activity on the mobile device and state of a battery powering the mobile device.

18. The method of claim 17 , wherein at least one of automatic speech processing and natural language processing is performed on the at least a portion of the acoustic input by the at least one server.

19. The method of claim 1 , wherein the mobile device is capable of connecting to at least one server via a network, the method further comprising transmitting at least a portion of the acoustic information to the at least one server via the network for processing by the at least one server.

20. A mobile device comprising:

at least one input configured to receive acoustic input from the environment of the mobile device while the mobile device is operating in a low power mode; and

at least one processor configured to:

detect whether the acoustic input includes a voice command from a user without requiring receipt of an explicit trigger from the user; and

initiate responding to the detected voice command.