Methods and systems for speech detection

1. A method of processing user input to a computing system having an audio input and a visual input, the method comprising:

receiving, at the computing system, an audio input signal from said audio input;

performing a determination of whether the user has demonstrated an intent to interact with the computing system via the audio input, wherein determining whether the user has demonstrated the intent to interact with the computing system via the audio input comprises:

performing a face detection method on an image received from the visual input after the audio input signal has been received; and

determining whether said face detection method has detected a face after the audio input signal has been received;

responsive to the determination that the user has demonstrated the intent to interact with the computing system via the audio input, confirming whether the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable by (i) performing additional verification operations comprising two or more of matching the face against a user profile of the user, determining whether the face is detected at an expected distance from a camera, or determining whether the face is detected at an expected angle with respect to the camera, and (ii) determining whether a weighted sum of results of the additional verification operations satisfies a threshold; and

responsive to confirming that the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable:

recording the audio input signal from said audio input; and

making said audio input signal available to a speech processing function.

2. The method of claim 1 , wherein said additional verification operations comprise a gaze direction detection operation to verify that the user is looking in a predefined direction or range of directions.

3. The method of claim 1 , wherein said additional verification operations comprise a mouth movement detection operation to verify that the user's mouth is moving.

4. The method of claim 3 , wherein said mouth movement detection operation further verifies that the mouth movement of the user corresponds to a movement pattern typical of speech.

5. The method of claim 1 , wherein said additional verification operations comprise an audio detection operation to verify that the audio input is receiving sound from the environment of the user.

6. The method of claim 5 , wherein said audio detection operation further verifies that the characteristics of detected sound are consistent with speech.

7. The method of claim 5 , wherein said audio detection operation further verifies that the direction from which sound is detected is consistent with the direction of the detected face.

8. The method of claim 5 , wherein said audio detection operation further verifies that the characteristics of detected sound are consistent with a speech profile stored for a given user.

9. The method of claim 1 , wherein said face detection operation verifies that the detected face is oriented in a predetermined direction or range of directions.

10. The method of claim 1 , wherein the face detection operation verifies that the visual input is at or below the level of the user's eyes or nose.

11. The method of claim 1 , further comprising performing said speech processing function on the recorded signal.

12. The method of claim 1 , further comprising sending said recorded audio signal to a remote computing device for speech processing.

13. The method of claim 1 , further comprising buffering said audio input signal, and (i) responsive to confirming that the determination that the user has demonstrated the intent to interact with the computing system via the audio input is not reliable, overwriting or discarding the buffered signal; and (ii) responsive to responsive to confirming that the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable, retrieving said audio input signal from the buffer.

14. The method of claim 12 , wherein said buffer is of sufficient capacity to store an audio input signal of a duration at least as long as the time required to determine the face detection and optionally the additional verification operations.

15. A computing system for processing user input having an audio input and a visual input, the system comprising:

a memory; and

a processor, coupled to the memory, to:

receive, at the computing system, an audio input signal from said audio input;

perform a determination of whether the user has demonstrated an intent to interact with the computing system via the audio input, wherein to determine whether the user has demonstrated the intent to interact with the computing system via the audio input, the processor is further to:

perform a face detection method on an image received from the visual input after the audio input signal has been received; and

determine whether said face detection method has detected a face after the audio input signal has been received;

responsive to the determination that the user has demonstrated the intent to interact with the computing system via the audio input, confirm whether the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable by (i) performing additional verification operations comprising two or more of matching the face against a user profile of the user, determining whether the face is detected at an expected distance from a camera, or determining whether the face is detected at an expected angle with respect to the camera, and (ii) determining whether a weighted sum of results of the additional verification operations satisfies a threshold; and

responsive to confirming that the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable:

record the audio input signal from said audio input; and

make said audio input signal available to a speech processing function.

16. A non-transitory computer readable medium comprising instructions, which when executed by a processor, cause the processor to perform a method of processing user input to a computing system having an audio input and a visual input, the method comprising:

receiving, at the computing system, an audio input signal from said audio input;

performing a determination of whether the user has demonstrated an intent to interact with the computing system via the audio input, wherein determining whether the user has demonstrated the intent to interact with the computing system via the audio input comprises:

performing a face detection method on an image received from the visual input after the audio input signal has been received; and

determining whether said face detection method has detected a face after the audio input signal has been received;

responsive to the determination that the user has demonstrated the intent to interact with the computing system via the audio input, confirming whether the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable by (i) performing additional verification operations comprising two or more of matching the face against a user profile of the user, determining whether the face is detected at an expected distance from a camera, or determining whether the face is detected at an expected angle with respect to the camera, and (ii) determining whether a weighted sum of results of the additional verification operations satisfies a threshold; and

responsive to confirming that the determination that the user has demonstrated the intent to interact with the computing system via the audio input is reliable:

recording the audio input signal from said audio input; and

making said audio input signal available to a speech processing function.