System and method for voice authentication

A device, comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium, comprising code executable by the processor, for performing a method for enrolling a user in an authentication system and conducting a transaction, the method comprising:
• receiving a user request;
• prompting a word string to be repeated by a user;
• recording a first audio segment originating from the user while the user attempts to vocally reproduce the prompted word string;
• and
• sending the first audio segment to a server computer, wherein the server computer generates a voice profile for the user based on the first audio segment, wherein the server computer stores the generated voice profile;
• playing a supplemental signal that is inaudible and that is unique to the transaction and that was provided to the device by the server computer;
• concurrently recording a third audio segment originating from the user, and the supplemental signal to form a second audio segment;
• and
• sending the second audio segment to the server computer, wherein the server computer authenticates the user by determining that the third audio segment matches the first audio segment in the voice profile, and that the supplemental signal in the second audio segment matches the supplemental signal provided by the server computer.

A method for enrolling a user in an authentication system and conducting a transaction, the method comprising:

• receiving, by a server computer, a first audio segment originating from a user while the user attempts to vocally reproduce a word string;
• generating, by the server computer, a voice profile for the user including the first audio segment;
• storing, by the server computer, the generated voice profile;
• providing, by the server computer to a device, a supplemental signal that is inaudible and is unique to the transaction, wherein the supplemental signal is subsequently played by the device and the device concurrently records a third audio segment, received from the user, and the supplemental signal to form a second audio segment;
• receiving, by the server computer and from the device, the second audio segment comprising the third audio segment and the supplemental signal;
• and
• authenticating, by the server computer, the user for the transaction by matching the third audio segment with the first audio segment, and matching the supplemental signal in the second audio segment with the supplemental signal provided by the server computer.

A server computer, comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium, comprising code executable by the processor, for performing a method for enrolling a user in an authentication system and conducting a transaction, the method comprising:
• receiving, from a device, a first audio segment originating from a user;
• generating a voice profile for the user based on the first audio segment;
• storing the generated voice profile;
• providing, to the device, a supplemental signal that is inaudible and that is unique to the transaction, wherein the supplemental signal is subsequently played by the device and the device concurrently records a third audio segment, received from the user, and the supplemental signal to form a second audio segment;
• receiving, from the device, the second audio segment comprising the third audio segment originating from the user and the supplemental signal;
• and
• authenticating the user for the transaction by matching the third audio segment with the first audio segment, and matching the supplemental signal in the second audio segment with the supplemental signal provided by the server computer.