Generation of voice profiles

• US 8,719,020 B1
• Filed: 01/07/2013
• Issued: 05/06/2014
• Est. Priority Date: 05/06/2010
• Status: Active Grant

• Current Assignee: T-Mobile Innovations LLC (Deutsche Telekom AG)
• Original Assignee: Sprint Communications Company LP (Deutsche Telekom AG)
• Inventors: Peden, Mark D., Youngs, Simon, Koller, Gary D., Jethwa, Piyush
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/735,597
• Time in Patent Office: 484 Days
• Field of Search: 704/246, 704/247, 704/249, 704/250, 704/233, 704/270.1
• US Class Current: 704/246
• CPC Class Codes: G10L 13/086 Detection of language
• CPC Class Codes: G10L 15/005 Language recognition

Abstract

Embodiments of the present invention provide systems, methods, and computer-readable media for generating a voice characteristic profile based on detected sound components. In embodiments, a call is initiated between a first caller and a second caller. Information communicated during the call is monitored to determine that sound components have been spoken by the first caller. The sound components are determined to be associated with a language dialect. Further, the sound components are stored in association with the first caller. In particular, the sound components are stored in association with the first caller in a voice characteristic profile of the first caller.

Claims

1. A method of generating and using voice characteristic profiles, the method comprising:

receiving, at a computing device, information communicated between a first caller'"'"'s device and a second caller'"'"'s device during a communication;

analyzing the information communicated by the first caller'"'"'s device;

identifying a set of sound components from the information communicated by the first caller'"'"'s device;

determining a first language characteristic for the information communicated by the first caller'"'"'s device, by matching a subset of the set of sound components with a threshold number of pre-defined sound components associated with the first language characteristic; and

using the first language characteristic to enhance the communication between the first caller'"'"'s device and the second caller'"'"'s device.

2. The method of claim 1, wherein the sound components are provided by a language characteristic recognition component.

3. The method of claim 1, wherein the subset of the set of sound components match a threshold number of pre-defined sound components associated with a plurality of language characteristics.

4. The method of claim 3, wherein a first language characteristic in the plurality of language characteristics, is prioritized above the remaining language characteristics in the plurality of language characteristics.

5. The method of claim 4, wherein the first language characteristic is prioritized based on the subset of the set of sound components matching the greatest number of pre-defined sound components associated with the first language characteristic.

6. The method of claim 1, wherein the first language characteristic is a first language dialect.

7. The method of claim 6, wherein using the first language characteristic to enhance the communication between the first caller'"'"'s device and the second caller'"'"'s device comprises modifying the information communicated by the second caller'"'"'s device based on the first language characteristic, and communicating the modified information to the first caller'"'"'s device during the communication between the first caller'"'"'s device and the second caller'"'"'s device.

8. The method of claim 7, wherein modifying the information communicated by the second caller'"'"'s device based on the first language characteristic, comprises modifying the information communicated by the second caller'"'"'s device to match the first language dialect.

9. The method of claim 1, wherein the first language characteristic is an age demographic.

10. The method of claim 9, wherein using the first language characteristic to enhance the communication between the first caller'"'"'s device and the second caller'"'"'s device comprises modifying the information communicated by the second caller'"'"'s device based on the first language characteristic by translating sound components that are absent from a word bank associated with the first language characteristic, and communicating the modified information to the first caller'"'"'s device during the communication between the first caller'"'"'s device and the second caller'"'"'s device.

11. The method of claim 10, wherein sound components that are absent from the word bank associated with the first language characteristic are translated to words in the first language characteristic with the closest definition to the sound components that are absent.

12. One or more non-transitory computer-readable media for storing information, having computer-executable instructions embodied thereon that, when executed by one or more computing devices, cause the one or more computing devices to perform a method of generating and using voice characteristic profiles, the method comprising:

receiving, at a computing device, information communicated between a first caller'"'"'s device and a second caller'"'"'s device during a communication;

analyzing the information communicated by a first caller on the first caller'"'"'s device;

identifying a set of sound components from the information communicated by the first caller;

determining a first language characteristic for the information communicated by the first caller, by matching a subset of the set of sound components with a threshold number of pre-defined sound components associated with the first language characteristic; and

using the first language characteristic associated with the first caller to modify information communicated by a second caller on the second caller'"'"'s device to match the first language characteristic associated with the first caller, to enhance the communication between the first caller'"'"'s device and the second caller'"'"'s device.

13. The media of claim 12, wherein the first language characteristic is a first language dialect.

14. The media of claim 13, wherein modifying the information communicated by the second caller'"'"'s device based on the first language characteristic, comprises modifying the information communicated by the second caller'"'"'s device to match the first language dialect.

15. The media of claim 12, wherein the first language characteristic is an age demographic.

16. The method of claim 12, wherein using the first language characteristic to enhance the communication between the first caller'"'"'s device and the second caller'"'"'s device comprises modifying the information communicated by the second caller'"'"'s device based on the first language characteristic by translating sound components that are absent from a word bank associated with the first language characteristic, and communicating the modified information to the first caller'"'"'s device during the communication between the first caller'"'"'s device and the second caller'"'"'s device.

17. The method of claim 16, wherein sound components that are absent from the word bank associated with the first language characteristic are translated to words in the first language characteristic with the closest definition to the sound components that are absent.

18. One or more non-transitory computer-readable media for storing information, having computer executable instructions embodied thereon that, when executed by one or more computing devices, cause the one or more computing devices to perform a method of modifying information communicated during a call based on voice characteristic profiles, the method comprising:

receiving, at a voice processing component in a computing device, information communicated during the call between a first caller and a second caller, the information spoken by the second caller;

retrieving, from a database, a voice characteristic profile associated with the first caller, the voice characteristic profile comprising a first characteristic;

determining a set of keywords associated with the first characteristic;

modifying the information spoken by the second caller based on the first characteristic and the set of keywords; and

communicating the information that is modified to the first caller.

19. The computer-readable media of claim 18, wherein the first characteristic is a first language dialect.

20. The computer-readable media of claim 18, wherein the first characteristic is an age demographic.