Systems and Methods for Continual Speech Recognition and Detection in Mobile Computing Devices

• US 20140244253A1
• Filed: 09/27/2012
• Published: 08/28/2014
• Est. Priority Date: 09/30/2011
• Status: Abandoned Application

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bringert, Bjorn Erik, Hodgson, Peter John, Pietryka, Pawel, Tickner, Simon, Cohen, Richard Zarek, Penha, Henrique, Zanolin, Luca, Burke, Dave
• Application Number:
  US14/347,456
• Publication Number:
  US 20140244253A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 21/10 Transforming into visible information

Abstract

The present application describes systems, articles of manufacture, and methods for continuous speech recognition for mobile computing devices. One embodiment includes determining whether a mobile computing device is receiving operating power from an external power source or a battery power source, and activating a trigger word detection subroutine in response to determining that the mobile computing device is receiving power from the external power source. In some embodiments, the trigger word detection subroutine operates continually while the mobile computing device is receiving power from the external power source. The trigger word detection subroutine includes determining whether a plurality of spoken words received via a microphone includes one or more trigger words, and in response to determining that the plurality of spoken words includes at least one trigger word, launching an application corresponding to the at least one trigger word included in the plurality of spoken words.

Claims

1-20. -20. (canceled)

21. A method comprising:

determining whether a computing device is receiving operating power from an external power source, wherein the computing device has a trigger word detection subroutine that is activatable by a user input and automatically in response to determining that the computing device is receiving external power; and

in response to determining that the computing device is receiving operating power from the external power source, taking a trigger word detection action, wherein the trigger word detection action includes;

receiving spoken input via a microphone of the computing device,

based on speech recognition performed on the spoken input, obtaining text,

determining whether the text includes one or more trigger words associated with for a voice command prompt action, and

in response to determining that the text includes the one or more trigger words associated with the voice command prompt action, taking the voice command prompt action, wherein the voice command prompt action is configured to receive via the microphone additional spoken input that causes the computing device to take one or more other actions, and wherein taking the voice command prompt action comprises displaying a voice command prompt on the computing device.

22. The method of claim 21, further comprising:

taking the trigger word detection action continually until it is deactivated.

23. The method of claim 21, further comprising:

deactivating the trigger word detection action in response to determining that the computing device is receiving operating power front one or more batteries.

24. The method of claim 21, further comprising:

receiving the user input; and

taking the trigger word detection action in response to receiving the user input regardless of whether the computing device is receiving operating power from the external power source.

25. The method of claim 21, wherein the one or more other actions include at least one of a communications action, a multimedia action, and an action for configuring settings of the computing device.

26. The method of claim 21, wherein the external power source is at least one of a charger associated with the computing device and a docking station for the computing device.

27. The method of claim 21, wherein one or more of the determining step, the launching step, and the trigger word detection action are components of a computing device operating system.

28. The method of claim 21, wherein the additional spoken input comprises a corresponding action that corresponds to the additional spoken input, and wherein the method further comprises:

in response to receiving the additional spoken input, taking the corresponding action on the computing device.

29. The method of claim 28, wherein the additional spoken input further includes one or more parameters, and wherein taking the corresponding action comprises taking the corresponding action based on the one or more parameters.

30. The computing device of claim 28, wherein the additional spoken input comprises an object of the corresponding action, and wherein taking the corresponding action comprises taking the corresponding action based on the object of the corresponding action.

31. A computing device comprising:

a sound detector;

a display;

a power selector configured to selectively power the computing device from one of either an external power source or one or more batteries; and

one or more processors configured for

continually taking a trigger word detection action while the power selector is powering the computing device from the external power source and stop taking the trigger word detection action when the power selector is powering the computing device from the one or more batteries,

wherein the trigger word detection action comprises determining whether spoken input received via the sound detector includes one or more trigger words associated with a voice command prompt action, and in response to determining that the spoken input includes the one or more trigger words associated with the voice command prompt action, taking the voice command prompt action, wherein the voice command prompt action is configured to receive via the sound detector additional spoken input that causes the computing device to take one or more other actions, and wherein taking the voice command prompt action comprises displaying a voice command prompt on the display.

32. The computing device of claim 31, further comprising:

a user interface configured to receive an input from a user to take the trigger word detection action when the power selector is powering the computing device from the one or more batteries.

33. The computing device of claim 31, wherein the one or more other applications include at least one of a communications application, a multimedia application, or an application for configuring settings of the computing device.

34. The computing device of claim 31, wherein the additional spoken input comprises a corresponding action that corresponds to the additional spoken input, and wherein the one or more processors are further configured to:

in response to receiving the additional spoken input, taking the corresponding action.

35. The computing device of claim 34, wherein the additional spoken input further includes one or more parameters associated with the corresponding action, and wherein taking the corresponding action comprises taking the corresponding action based on the one or more parameters.

36. The computing device of claim 34, wherein the additional spoken input comprises an object of the corresponding action, and wherein taking the corresponding action comprises taking the corresponding action based on the object of the corresponding action

37. A non-transitory computer readable medium having stored therein executable instructions that, when executed by a computing device having at least one processor, causes the computing device to perform functions comprising:

determining whether the computing device is receiving operating power from either an external power source or an internal batter source; and

in response to determining that the computing device is receiving operating power from the external power source, taking a trigger word detection action, wherein the trigger word detection action includes;

continually determining whether spoken input received via a microphone includes one or more trigger words associated with an action for a voice command prompt and,

in response to determining that the spoken input includes the one or more trigger words associated with the voice command prompt, taking the action for the voice command prompt, wherein the voice command prompt is configured to receive via the microphone additional spoken input that causes the computing device to take one or more other actions, and wherein taking the action for the voice command prompt comprises displaying a voice command prompt on the computing device.

38. The non-transitory computer readable medium of claim 37, wherein the functions further comprise:

deactivating the trigger word detection subroutine in response to determining that the computing device is receiving operating power from the internal battery source.

39. The non-transitory computer readable medium of claim 37, wherein the functions further comprise:

receiving a user input; and

taking the trigger word detection action in response to receiving the user input regardless of whether the computing device is receiving operating power from the external power source.

40. The non-transitory computer readable medium of claim 37, wherein the additional spoken input comprises a corresponding action that corresponds to the additional spoken input, and wherein the functions further comprise:

in response to receiving the additional spoken input, taking the corresponding action on the computing device.