Speech transaction processing
Embodiments of the invention are directed to systems and methods for speech transaction processing. A location of a device associated with a user may be determined. A reference to a voice model associated with the user stored within a database may be retrieved, based at least in part on the location. A voice segment may be received from the user. Using the reference, the voice segment may be compared to the voice model stored within the database. A determination may be made whether the user is authenticated for the transaction based on the comparing step.
1. A method of authenticating a user for a transaction, the method comprising:
receiving, at a server computer, a communication indicative of the communication device associated with the user entering a location within a virtual perimeter;
in response to receiving the communication and prior to receiving a voice segment from the user, retrieving, via the server computer, a reference for accessing a voice model associated with the user, wherein the voice model is stored in a database, wherein the reference is a pointer to a storage address within the database;
using, at the server computer, the reference to access the voice model stored in the database;
comparing, at the server computer, the received voice segment to the voice model;
determining, at the server computer, whether the user is authenticated for the transaction based at least in part on comparing the received voice segment to the voice model; and
transmitting, via the server computer and to a merchant computer, a result of the determining step.
2. The method of claim 1 , wherein the database is a first database, the method further comprising:
using the reference, copying the voice model from the first database to a second database, wherein the voice model being compared with the received voice segment is retrieved from the second database.
3. The method of claim 1 , wherein the comparing step further comprises determining a match score based at least in part on the comparison.
4. The method of claim 1 , wherein the virtual perimeter is established around a merchant location.
5. The method of claim 1 , further comprising updating the voice model with the received voice segment.
6. The method of claim 1 , wherein the voice model is based on a plurality of voice segments previously received from the user.
7. The method of claim 1 , further comprising:
calculating a match score based at least in part on comparing the received voice segment to the voice model; and
approving or declining the transaction based on the match score.
8. A server computer, comprising:
a processor; and
a non-transitory computer-readable storage medium, comprising code executable by the processor for implementing a method for authenticating a user for a transaction, the method comprising:
receiving a communication indicative of the communication device associated with the user entering a location within a virtual perimeter;
in response to receiving the communication and prior to receiving a voice segment from the user, retrieving a reference for accessing a voice model associated with the user, wherein the voice model is stored in a database, wherein the reference is a pointer to a storage address within the database;
using the reference to access the voice model stored in the database;
comparing the received voice segment to the voice model;
determining whether the user is authenticated for the transaction based at least in part on comparing the received voice segment to the voice model; and
transmitting, to a merchant computer, a result of the determining step.
9. The server computer of claim 8 , wherein the database is a first database, the method further comprising:
using the reference, copying the voice model from the first database to a second database, wherein the voice model being compared with the received voice segment is retrieved from the second database.
10. The server computer of claim 8 , wherein the comparing step further comprises determining a match score based at least in part on the comparison.
11. The server computer of claim 8 , wherein the virtual perimeter is established around a merchant location.
12. The server computer of claim 8 , further comprising updating the voice model with the received voice segment.
13. The server computer of claim 8 , wherein the voice model is based on a plurality of voice segments previously received from the user.
14. The server computer of claim 8 , further comprising:
calculating a match score based at least in part on comparing the received voice segment to the voice model; and
approving or declining the transaction based on the match score.