Multi-mode guard for voice commands

Abstract

Embodiments may be implemented by a computing device, such as a head-mountable display, in order to use a single guard phrase to enable different voice commands in different interface modes. An example device includes an audio sensor and a computing system configured to analyze audio data captured by the audio sensor to detect speech that includes a predefined guard phrase, and to operate in a plurality of different interface modes comprising at least a first and a second interface mode. During operation in the first interface mode, the computing system may initially disable one or more first-mode speech commands, and respond to detection of the guard phrase by enabling the one or more first-mode speech commands. During operation in the second interface mode, the computing system may initially disable a second-mode speech command, and to respond to the guard phrase by enabling the second-mode speech command.

We claim: 
     
         1 . A method implemented by one or more processors of a computing device, the method comprising:
 transitioning the computing device into a given interface mode in response to receiving sensor data captured by at least one sensor of the computing device;   in response to the computing device being in the given interface mode:
 activating one or more speech commands that are specific to the given interface mode,
 wherein the given interface mode corresponds to a current state of a user interface of the computing device, and 
 wherein the given interface mode is one of multiple interface modes each corresponding to corresponding alternate states of the user interface; 
 
   while the computing device is in the given interface mode and while the one or more speech commands are activated:
 receiving audio data captured by at least one audio sensor of the computing device; 
 analyzing, based on the one or more speech commands being activated, the audio data to determine whether any of the one or more speech commands are included in the audio data; 
 in response to determining a given speech command, of the one or more speech commands, is included in the audio data without a predefined guard phrase, and in response to determining that the audio data is received within a predetermined period of time of transitioning the computing device into the given interface mode:
 performing one or more actions, via the computing device, that correspond to the given speech command. 
 
   
     
     
         2 . The method of  claim 1 , further comprising:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 determining the predetermined period of time has lapsed; and 
 in response to determining the predetermined period of time has lapsed, 
   deactivating one or more of the speech commands that are specific to the given interface mode.   
     
     
         3 . The method of  claim 2 , further comprising:
 while the computing device is in the given interface mode and while the one or more speech commands are deactivated:
 in response to determining the given speech command, of the one or more speech commands, is included in the audio data without the predefined guard phrase, and in response to determining that the audio data is not received within the predetermined period of time:
 refraining from performing one or more of the actions, via the computing device, that correspond to the given speech command. 
 
   
     
     
         4 . The method of  claim 3 , further comprising:
 subsequent to refraining from performing one or more of the actions, via the computing device, that correspond to the given speech command:
 receiving additional audio data captured by the at least one audio sensor of the computing device, the additional audio data including at least the predefined guard phrase; and 
 re-activating one or more speech of the commands that are specific to the given interface mode. 
   
     
     
         5 . The method of  claim 1 , further comprising:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 displaying a visual cue for one or more of the speech commands via a display of the computing device. 
   
     
     
         6 . The method of  claim 5 , further comprising:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 determining the predetermined period of time has lapsed; and 
 in response to determining the predetermined period of time has lapsed, causing the visual cue for the one or more speech commands to be removed from the display of the computing device. 
   
     
     
         7 . The method of  claim 1 ,
 wherein activating the one or more speech commands that are specific to the given interface mode comprises loading, at the computing device, at least one hotword process for the one or more speech commands; and   wherein analyzing, based on the one or more speech commands being activated, the audio data to determine whether any of the one or more speech commands are included in the audio data comprises:
 analyzing the audio data using the at least one hotword process. 
   
     
     
         8 . The method of  claim 1 , wherein the sensor data captured by the at least one sensor of the computing device comprises preceding audio data captured by the at least one audio sensor of the computing device, the preceding audio data including at least the predefined guard phrase and an indication of the given interface mode. 
     
     
         9 . The method of  claim 1 , wherein the predetermined period of time is specific to the given interface mode. 
     
     
         10 . The method of  claim 1 , wherein activating one or more of the speech commands in based on the first audio data. 
     
     
         11 . The method of  claim 1 , wherein the computing device is a head-mountable device. 
     
     
         12 . A computing device including memory and one or more processors configured to execute instructions stored in memory, the instructions comprising instructions to:
 transition the computing device into a given interface mode in response to receiving sensor data captured by at least one sensor of the computing device;   in response to the computing device being in the given interface mode:
 activate one or more speech commands that are specific to the given interface mode,
 wherein the given interface mode corresponds to a current state of a user 
 
 interface of the computing device, and
 wherein the given interface mode is one of multiple interface modes each corresponding to corresponding alternate states of the user interface; 
 
   while the computing device is in the given interface mode and while the one or more speech commands are activated:
 receive audio data captured by at least one audio sensor of the computing device; 
 analyze, based on the one or more speech commands being activated, the audio data to determine whether any of the one or more speech commands are included in the audio data; 
 in response to determining a given speech command, of the one or more speech commands, is included in the audio data without a predefined guard phrase, and in response to determining that the audio data is received within a predetermined period of time of transitioning the computing device into the given interface mode:
 perform one or more actions, via the computing device, that correspond to the given speech command. 
 
   
     
     
         13 . The computing device of  claim 12 , wherein the instructions further comprise instructions to:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 determine the predetermined period of time has lapsed; and 
 in response to determining the predetermined period of time has lapsed, deactivate one or more of the speech commands that are specific to the given interface mode. 
   
     
     
         14 . The computing device of  claim 13 , wherein the instructions further comprise instructions to:
 while the computing device is in the given interface mode and while the one or more speech commands are deactivated:
 in response to determining the given speech command, of the one or more speech commands, is included in the audio data without the predefined guard phrase, and in response to determining that the audio data is not received within the predetermined period of time:
 refrain from performing one or more of the actions, via the computing device, that correspond to the given speech command. 
 
   
     
     
         15 . The computing device of  claim 14 , wherein the instructions further comprise instructions to:
 subsequent to refraining from performing one or more of the actions, via the computing device, that correspond to the given speech command:
 receive additional audio data captured by the at least one audio sensor of the computing device, the additional audio data including at least the predefined guard phrase; and 
 re-activate one or more speech of the commands that are specific to the given interface mode. 
   
     
     
         16 . The computing device of  claim 12 , wherein the instructions further comprise instructions to:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 display a visual cue for one or more of the speech commands via a display of the computing device. 
   
     
     
         17 . The computing device of  claim 16 , wherein the instructions further comprise instructions to:
 while the computing device is in the given interface mode and while the one or more speech commands are activated:
 determine the predetermined period of time has lapsed; and 
 in response to determining the predetermined period of time has lapsed, cause the visual cue for the one or more speech commands to be removed from the display of the computing device. 
   
     
     
         18 . The computing device of  claim 12 ,
 wherein the instructions to activate the one or more speech commands that are specific to the given interface mode comprise instructions to load, at the computing device, at least one hotword process for the one or more speech commands; and   wherein the instructions to analyze, based on the one or more speech commands being activated, the audio data to determine whether any of the one or more speech commands are included in the second audio data comprise instructions to:
 analyze the audio data using the at least one hotword process. 
   
     
     
         19 . The computing device of  claim 12 , wherein the sensor data captured by the at least one sensor of the computing device comprises preceding audio data captured by the at least one audio sensor of the computing device, the preceding audio data including at least the predefined guard phrase and an indication of the given interface mode. 
     
     
         20 . A non-transitory computer-readable storage medium storing instructions executable by at least one processor, the instructions including instructions to:
 transition the computing device into a given interface mode in response to receiving sensor data captured by at least one sensor of the computing device;   in response to the computing device being in the given interface mode:
 activate one or more speech commands that are specific to the given interface mode,
 wherein the given interface mode corresponds to a current state of a user interface of the computing device, and 
 wherein the given interface mode is one of multiple interface modes each corresponding to corresponding alternate states of the user interface; 
 
   while the computing device is in the given interface mode and while the one or more speech commands are activated:
 receive audio data captured by at least one audio sensor of the computing device; 
 analyze, based on the one or more speech commands being activated, the audio data to determine whether any of the one or more speech commands are included in the audio data; 
 in response to determining a given speech command, of the one or more speech commands, is included in the audio data without a predefined guard phrase, and in response to determining that the audio data is received within a predetermined period of time of transitioning the computing device into the given interface mode: 
 perform one or more actions, via the computing device, that correspond to the given speech command.