User presence detection

Abstract

A speech-capture device can capture audio data during wakeword monitoring and use the audio data to determine if a user is present nearby the device, even if no wakeword is spoken. Audio such as speech, human originating sounds (e.g., coughing, sneezing), or other human related noises (e.g., footsteps, doors closing) can be used to detect audio. Audio frames are individually scored as to whether a human presence is detected in the particular audio frames. The scores are then smoothed relative to nearby frames to create a decision for a particular frame. Presence information can then be sent according to a periodic schedule to a remote device to create a presence “heartbeat” that regularly identifies whether a user is detected proximate to a speech-capture device.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method, comprising:
 determining presence data indicating that a user is present in an environment of a first device;   determining a second device corresponds to a prior unsuccessful request to initiate a communication from the second device to the first device; and   sending, to the second device, an indication that the user is present in the environment.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the first device is capable of being controlled through a far field voice interface. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the presence data is based at least in part on audio data captured by at least one microphone of the first device. 
     
     
         24 . The computer-implemented method of  claim 23 , wherein the audio data represents speech in the environment. 
     
     
         25 . The computer-implemented method of  claim 23 , wherein the audio data comprises data corresponding to a plurality of audio frames. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein the presence data is based at least in part on camera data representing the environment. 
     
     
         27 . The computer-implemented method of  claim 21 , wherein the presence data corresponds to output of a machine learning model. 
     
     
         28 . The computer-implemented method of  claim 21 , wherein the presence data is based at least in part on a signal from a third device. 
     
     
         29 . The computer-implemented method of  claim 21 , further comprising:
 determining a first user profile associated with the first device; and   determining the second device is associated with contact data corresponding to the first user profile.   
     
     
         30 . The computer-implemented method of  claim 21 , further comprising:
 determining permission data indicating that the second device is permitted to receive presence information corresponding to the first device.   
     
     
         31 . A system comprising:
 at least one processor; and   at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
 determine presence data indicating that a user is present in an environment of a first device; 
 determine a second device corresponds to a prior unsuccessful request to initiate a communication from the second device to the first device; and 
 send, to the second device, an indication that the user is present in the environment. 
   
     
     
         32 . The system of  claim 31 , wherein the first device is capable of being controlled through a far field voice interface. 
     
     
         33 . The system of  claim 31 , wherein the presence data is based at least in part on audio data captured by at least one microphone of the first device. 
     
     
         34 . The system of  claim 33 , wherein the audio data represents speech in the environment. 
     
     
         35 . The system of  claim 34 , wherein the audio data comprises data corresponding to a plurality of audio frames. 
     
     
         36 . The system of  claim 31 , wherein the presence data is based at least in part on camera data representing the environment. 
     
     
         37 . The system of  claim 31 , wherein the presence data corresponds to output of a machine learning model. 
     
     
         38 . The system of  claim 31 , wherein the presence data is based at least in part on a signal from a third device. 
     
     
         39 . The system of  claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine a first user profile associated with the first device; and   determine the second device is associated with contact data corresponding to the first user profile.   
     
     
         40 . The system of  claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine permission data indicating that the second device is permitted to receive presence information corresponding to the first device.