Securing audio data

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for securing audio data. In one aspect, a method includes restricting access by the device to audio information detected by a microphone, receiving data indicating that the device is authorized to access audio information detected by the microphone during a limited period of time, and in response to receiving data indicating that the device is authorized to access audio information detected by the microphone during the limited period of time, providing audio information to the device. The method also includes monitoring audio information detected by the microphone during the limited period of time for the presence of a hotword and after the end of the limited period of time, restricting access by the device to audio information detected by the microphone.

What is claimed is: 
     
         1 . A method comprising:
 obtaining audio information by a microphone of a first device, wherein the audio information includes a first portion, a second portion detected subsequent to detection of the first portion, and a third portion detected subsequent to detection of the second portion;   providing the first portion of the audio information to a second device;   detecting a presence of a hotword in the second portion audio information, wherein the hotword signals a beginning of a voice request;   in response to detecting the presence of the hotword in the second portion of the audio information, blocking the second portion of the audio information from being provided to the second device;   detecting an end of the voice request in the second portion of the audio information; and   in response to detecting the end of the voice request in the second portion of the audio information, providing the third portion of the audio information to the second device.   
     
     
         2 . The method of  claim 1 , wherein detecting a presence of a hotword in the second portion audio information comprises:
 detecting speech corresponding to a predetermined phrase in the second portion audio information.   
     
     
         3 . The method of  claim 1 , wherein detecting an end of the voice request in the second portion of the audio information comprises:
 detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information.   
     
     
         4 . The method of  claim 1 , wherein detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information comprises:
 determining that the pause in speech of the user has a duration that satisfies a criteria based on predetermined length of time.   
     
     
         5 . The method of  claim 1 , wherein blocking the second portion of the audio information from being provided to the second device comprises:
 providing the second portion of the audio information to a voice request server instead of the second device.   
     
     
         6 . The method of  claim 5 , wherein providing the second portion of the audio information to a voice request server instead of the second device comprises:
 encrypting the second portion of the audio information; and   providing the second portion of the audio information in the encrypted form to a processor in the device for the processor to provide to the voice request server instead of the second device.   
     
     
         7 . The method of  claim 1 , wherein providing the third portion of the audio information to the second device comprises:
 detecting that the third portion of the audio information likely does not include a follow-up request; and   in response to detecting that the third portion of the audio information likely does not include a follow-up request, providing the third portion of the audio information to the second device.   
     
     
         8 . The method of  claim 1 , wherein providing the third portion of the audio information to the second device comprises:
 detecting that a predetermined amount of time has passed since the end of the voice request was detected; and   in response to detecting that a predetermined amount of time has passed since the end of the voice request was detected, providing the third portion of the audio information to the second device.   
     
     
         9 . A system comprising:
 one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:   obtaining audio information by a microphone of a first device, wherein the audio information includes a first portion, a second portion detected subsequent to detection of the first portion, and a third portion detected subsequent to detection of the second portion;   providing the first portion of the audio information to a second device;   detecting a presence of a hotword in the second portion audio information, wherein the hotword signals a beginning of a voice request;   in response to detecting the presence of the hotword in the second portion of the audio information, blocking the second portion of the audio information from being provided to the second device;   detecting an end of the voice request in the second portion of the audio information; and   in response to detecting the end of the voice request in the second portion of the audio information, providing the third portion of the audio information to the second device.   
     
     
         10 . The system of  claim 9 , wherein detecting a presence of a hotword in the second portion audio information comprises:
 detecting speech corresponding to a predetermined phrase in the second portion audio information.   
     
     
         11 . The system of  claim 9 , wherein detecting an end of the voice request in the second portion of the audio information comprises:
 detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information.   
     
     
         12 . The system of  claim 9 , wherein detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information comprises:
 determining that the pause in speech of the user has a duration that satisfies a criteria based on predetermined length of time.   
     
     
         13 . The system of  claim 9 , wherein blocking the second portion of the audio information from being provided to the second device comprises:
 providing the second portion of the audio information to a voice request server instead of the second device.   
     
     
         14 . The system of  claim 13 , wherein providing the second portion of the audio information to a voice request server instead of the second device comprises:
 encrypting the second portion of the audio information; and   providing the second portion of the audio information in the encrypted form to a processor in the device for the processor to provide to the voice request server instead of the second device.   
     
     
         15 . The system of  claim 9 , wherein providing the third portion of the audio information to the second device comprises:
 detecting that the third portion of the audio information likely does not include a follow-up request; and   in response to detecting that the third portion of the audio information likely does not include a follow-up request, providing the third portion of the audio information to the second device.   
     
     
         16 . The system of  claim 9 , wherein providing the third portion of the audio information to the second device comprises:
 detecting that a predetermined amount of time has passed since the end of the voice request was detected; and   in response to detecting that a predetermined amount of time has passed since the end of the voice request was detected, providing the third portion of the audio information to the second device.   
     
     
         17 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
 obtaining audio information by a microphone of a first device, wherein the audio information includes a first portion, a second portion detected subsequent to detection of the first portion, and a third portion detected subsequent to detection of the second portion;   providing the first portion of the audio information to a second device;   detecting a presence of a hotword in the second portion audio information, wherein the hotword signals a beginning of a voice request;   in response to detecting the presence of the hotword in the second portion of the audio information, blocking the second portion of the audio information from being provided to the second device;   detecting an end of the voice request in the second portion of the audio information; and   in response to detecting the end of the voice request in the second portion of the audio information, providing the third portion of the audio information to the second device.   
     
     
         18 . The medium of  claim 17 , wherein detecting a presence of a hotword in the second portion audio information comprises:
 detecting speech corresponding to a predetermined phrase in the second portion audio information.   
     
     
         19 . The medium of  claim 17 , wherein detecting an end of the voice request in the second portion of the audio information comprises:
 detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information.   
     
     
         20 . The medium of  claim 17 , wherein detecting a pause in speech of a user at the end of audio represented by the second portion of the audio information comprises:
 determining that the pause in speech of the user has a duration that satisfies a criteria based on predetermined length of time.