Generating sensor-based identifier

Abstract

Examples of creating a device identifier that are based upon hardware components of a client device are discussed. An inaudible or high frequency reference audio sample is played. Audio capture is initiated using the microphone system. A sensor-based device identifier can be generated from the captured audio due the manufacturing variances in the hardware components used for the speaker and microphone systems.

1 . A system, comprising:
 a client device comprising a processor, a speaker system, and a microphone system; and   an application executed by the processor, wherein the application causes the client device to at least:
 generate a request to authenticate the client device, the request being transmitted from the client device to a computing device over a network; 
 receive a request to generate a sensor-based identifier of the client device from the computing device; 
 in response to receiving the request to generate the sensor-based identifier, initiate playback of a high-frequency reference sample through the speaker system; 
 initiate capture of an audio sample using the microphone system of the client device, the audio sample comprising the high-frequency reference sample and ambient noise; 
 transmit the audio sample to the computing device, wherein the computing device authenticates the sensor-based identifier of the client device based upon the audio sample and a previously generated sensor-based identifier that is stored in a data store accessible to the computing device; and 
 receive an indication of whether the client device has been authenticated by the client device over the network. 
   
     
     
         2 . The system of claim Error! Bookmark not defined., wherein the client device causes creation of the previously generated sensor-based identifier by at least:
 initiating playback of the high-frequency reference sample through the speaker system;   initiating capture of another audio sample using the microphone system of the client device; and   transmitting the other audio sample to the computing device, wherein the computing device generates the previously generated sensor-based identifier based upon the other audio sample.   
     
     
         3 . The system of claim Error! Bookmark not defined., wherein the other audio sample is longer than the audio sample. 
     
     
         4 . The system of claim Error! Bookmark not defined., wherein the high-frequency reference sample is ultrasonic. 
     
     
         5 . The system of claim Error! Bookmark not defined., wherein the high-frequency reference sample is greater than about 18 kHz. 
     
     
         6 . The system of claim Error! Bookmark not defined., wherein the computing device generates the sensor-based identifier by:
 performing a noise suppression algorithm to remove the ambient noise from the audio sample;   extracting at least one acoustic feature from the audio sample; and   generating the sensor-based identifier by generating a fingerprint from the at least one acoustic feature.   
     
     
         7 . The system of claim Error! Bookmark not defined., wherein the application initiates capture of the audio sample by:
 initiating playback of the high-frequency reference sample;   initiating audio capture of a first sample using the microphone system during playback of the high-frequency reference sample;   ceasing playback of the high-frequency reference sample; and   initiating audio capture of second sample using the microphone system when playback of the high-frequency reference sample is ceased; wherein,   the audio sample comprises the first sample including the high-frequency reference sample and the second sample that does not include the high frequency audio sample.   
     
     
         8 . A method comprising:
 generating a request to authenticate a client device, the request being transmitted from the client device to a computing device over a network;   receiving a request to generate a sensor-based identifier of the client device from the computing device;   in response to receiving the request to generate the sensor-based identifier, initiating playback of a high-frequency reference sample through a speaker system;   initiating capture of an audio sample using a microphone system of the client device, the audio sample comprising the high-frequency reference sample and ambient noise;   transmitting the audio sample to the computing device, wherein the computing device authenticates the sensor-based identifier of the client device based upon the audio sample and a previously generated sensor-based identifier that is stored in a data store accessible to the computing device; and   receiving an indication of whether the client device has been authenticated by the client device over the network.   
     
     
         9 . The method of claim Error! Bookmark not defined., wherein causing creation of the previously generated sensor-based identifier further comprises:
 initiating playback of the high-frequency reference sample through the speaker system;   initiating capture of another audio sample using the microphone system of the client device; and   transmitting the other audio sample to the computing device, wherein the computing device generates the previously generated sensor-based identifier based upon the other audio sample.   
     
     
         10 . The method of claim Error! Bookmark not defined., wherein the other audio sample is longer than the audio sample. 
     
     
         11 . The method of claim Error! Bookmark not defined., wherein the high-frequency reference sample is ultrasonic. 
     
     
         12 . The method of claim Error! Bookmark not defined., wherein the high-frequency reference sample is greater than about 18 kHz. 
     
     
         13 . The method of claim Error! Bookmark not defined., wherein generating the sensor-based identifier further comprises:
 performing a noise suppression algorithm to remove the ambient noise from the audio sample;   extracting at least one acoustic feature from the audio sample; and   generating the sensor-based identifier by generating a fingerprint from the at least one acoustic feature.   
     
     
         14 . The method of claim Error! Bookmark not defined., wherein initiating capture of the audio sample further comprises:
 initiating playback of the high-frequency reference sample;   initiating audio capture of a first sample using the microphone system during playback of the high-frequency reference sample;   ceasing playback of the high-frequency reference sample; and   initiating audio capture of second sample using the microphone system when playback of the high-frequency reference sample is ceased; wherein,   the audio sample comprises the first sample including the high frequency audio sample and the second sample that does not include the high frequency audio sample.   
     
     
         15 . A non-transitory computer-readable medium embodying a program executable on a client device, wherein the program, when executed, causes the client device to at least:
 generate a request to authenticate the client device, the request being transmitted from the client device to a computing device over a network;   receive a request to generate a sensor-based identifier of the client device from the computing device;   in response to receiving the request to generate the sensor-based identifier, initiate playback of a high-frequency reference sample through a speaker system;   initiate capture of an audio sample using a microphone system of the client device, the audio sample comprising the high-frequency reference sample and ambient noise;   transmit the audio sample to the computing device, wherein the computing device authenticates the sensor-based identifier of the client device based upon the audio sample and a previously generated sensor-based identifier that is stored in a data store accessible to the computing device; and   receive an indication of whether the client device has been authenticated by the client device over the network.   
     
     
         16 . The non-transitory computer-readable medium of claim Error! Bookmark not defined., wherein the program causes creation of the previously generated sensor-based identifier by at least:
 initiating playback of the high-frequency reference sample through the speaker system;   initiating capture of another audio sample using the microphone system of the client device; and   transmitting the other audio sample to the computing device, wherein the computing device generates the previously generated sensor-based identifier based upon the other audio sample.   
     
     
         17 . The non-transitory computer-readable medium of claim Error! Bookmark not defined., wherein the other audio sample is longer than the audio sample. 
     
     
         18 . The non-transitory computer-readable medium of claim Error! Bookmark not defined., wherein the high-frequency reference sample is greater than about 18 kHz. 
     
     
         19 . The non-transitory computer-readable medium of claim Error! Bookmark not defined., wherein the computing device generates the sensor-based identifier by:
 performing a noise suppression algorithm to remove the ambient noise from the audio sample;   extracting at least one acoustic feature from the audio sample; and   generating the sensor-based identifier by generating a fingerprint from the at least one acoustic feature.   
     
     
         20 . The non-transitory computer-readable medium of claim Error! Bookmark not defined., wherein the program initiates capture of the audio sample by:
 initiating playback of the high-frequency reference sample;   initiating audio capture of a first sample using the microphone system during playback of the high-frequency reference sample;   ceasing playback of the high-frequency reference sample; and   initiating audio capture of second sample using the microphone system when playback of the high-frequency reference sample is ceased; wherein,   the audio sample comprises the first sample including the high frequency audio sample and the second sample that does not include the high frequency audio sample.