System and method for auditory captchas

Abstract

Disclosed herein are systems, methods, and computer readable-media for performing an audible human verification. The method includes determining that a human verification is needed, presenting an audible challenge to a user which exploits a known issue with automatic speech recognition processes, receiving a response to the audible challenge, and verifying that a human provided the response. The known issue with automatic speech recognition processes can be recognition of a non-word, in which case the user can be asked to spell the recognized non-word. The known issue with automatic speech recognition processes can be differentiation of simultaneous input for multiple audio streams. Multiple audio streams contained in the audible challenge can be provided monaurally. Verifying that a human provided the response can include confirming the contents of one of the multiple audio streams. Audible human verification can be performed in combination with visual human verification.

We claim: 
     
         1 . A method comprising:
 presenting an audible challenge to a user device which exploits a previously detected issue with automatic speech recognition processes, where the audible challenge comprises presenting an audible pronunciation of a non-word pronounced like a single word, wherein the non-word does not exist in a vocabulary of natural languages, and requesting a user of the user device to spell the non-word;   receiving an audible response to the audible challenge; and   verifying an identity of the user based on the audible response.   
     
     
         2 . The method of  claim 1 , wherein the previously detected issue with automatic speech recognition processes further comprises spelling of the non-word. 
     
     
         3 . The method of  claim 1 , further comprising receiving multiple audio streams simultaneously, wherein one of the multiple audio streams is the audible response. 
     
     
         4 . The method of  claim 3 , wherein the previously detected issue with automatic speech recognition processes is differentiation of simultaneous input for the multiple audio streams. 
     
     
         5 . The method of  claim 3 , wherein, when the audible challenge is provided in digital form, the multiple audio streams contained in the audible challenge are provided monaurally. 
     
     
         6 . The method of  claim 3 , wherein verifying the identity of the user comprises analyzing contents of one of the multiple audio streams. 
     
     
         7 . The method of  claim 1 , wherein the audible challenge comprises a plurality of different words, where one of the plurality of different words is the non-word and another of the plurality of different words is a word which exists in the vocabulary of natural languages. 
     
     
         8 . A system comprising:
 a processor; and   a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprise:
 presenting an audible challenge to a user device which exploits a previously detected issue with automatic speech recognition processes, where the audible challenge comprises presenting an audible pronunciation of a non-word pronounced like a single word, wherein the non-word does not exist in a vocabulary of natural languages, and requesting a user of the user device to spell the non-word; 
 receiving an audible response to the audible challenge; and 
 verifying an identity of the user based on the audible response. 
   
     
     
         9 . The system of  claim 8 , wherein the previously detected issue with automatic speech recognition processes further comprises spelling of the non-word. 
     
     
         10 . The system of  claim 8 , the computer-readable storage medium having additional instructions stored which result in operations comprising receiving multiple audio streams, wherein one of the multiple audio streams is the audible response. 
     
     
         11 . The system of  claim 10 , wherein the previously detected issue with automatic speech recognition processes is differentiation of simultaneous input for the multiple audio streams. 
     
     
         12 . The system of  claim 10 , wherein, when the audible challenge is provided in digital form, the multiple audio streams contained in the audible challenge are provided monaurally. 
     
     
         13 . The system of  claim 10 , wherein verifying the identity of the user comprises analyzing contents of one of the multiple audio streams. 
     
     
         14 . The system of  claim 8 , wherein the audible challenge comprises a plurality of different words, where one of the plurality of different words is the non-word and another of the plurality of different words is a word which exists in the vocabulary of natural languages. 
     
     
         15 . A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprise:
 presenting an audible challenge to a user device which exploits a previously detected issue with automatic speech recognition processes, where the audible challenge comprises presenting an audible pronunciation of a non-word pronounced like a single word, wherein the non-word does not exist in a vocabulary of natural languages, and requesting a user of the user device to spell the non-word;   receiving an audible response to the audible challenge; and   verifying an identity of the user based on the audible response.   
     
     
         16 . The computer-readable storage device of  claim 15 , wherein the previously detected issue with automatic speech recognition processes further comprises spelling of the non-word. 
     
     
         17 . The computer-readable storage device of  claim 15 , having additional instructions stored which result in operations comprising receiving multiple audio streams, wherein one of the multiple audio streams is the audible response. 
     
     
         18 . The computer-readable storage device of  claim 17 , wherein the previously detected issue with automatic speech recognition processes is differentiation of simultaneous input for the multiple audio streams. 
     
     
         19 . The computer-readable storage device of  claim 17 , wherein, when the audible challenge is provided in digital form, the multiple audio streams contained in the audible challenge are provided monaurally. 
     
     
         20 . The computer-readable storage device of  claim 17 , wherein verifying the identity of the user comprises analyzing contents of one of the multiple audio streams.