Methods and systems for providing changes to a live voice stream

Patent metadata

Field	Value
Publication number	US-12057134-B2
Application number	US-202318168881-A
Country	US
Kind code	B2
Filing date	Feb 14, 2023
Priority date	May 29, 2019
Publication date	Aug 6, 2024
Grant date	Aug 6, 2024

Abstract

Methods and systems for providing changes to a live voice stream of a person are disclosed. A change to be made to the live voice stream based on user information can be identified. The live voice stream can be changed based on the user information.

First claim

The invention claimed is:

1. A computer-implemented method for providing changes to a voice stream output from a device of an entity, the method comprising:
retrieving, by a computer system, user information for an identified user interacting with the voice stream output by the device;
determining, by a neural network, if the user information indicates help is needed for the identified user to understand the voice stream;
identifying, by the computer system, a change to be made to the voice stream output by the device based on retrieved user information;
changing the voice stream output by the device, by a computerized voice changer, as identified by the user information; and
providing, by the computer system, a changed live voice stream output by the device to interact with the identified user.

2. The method of claim 1 , wherein the device is a mobile device.

3. The method of claim 1 , wherein the device interacts with the user via a mobile device application.

4. The method of claim 1 , wherein the device is at an establishment's physical site.

5. The method of claim 1 , wherein the device is at an entity's physical mobile site.

6. The method of claim 1 , wherein the live voice stream is from a kiosk and/or an automatic teller machine (ATM).

7. The method of claim 1 , wherein the change comprises a frequency change.

8. The method of claim 1 , wherein the change comprises an intonation change.

9. The method of claim 1 , wherein the change comprises a volume change.

10. The method of claim 1 , wherein the change comprises an accent change.

11. The method of claim 1 , wherein the change comprises a language change.

12. A system for providing changes to a live voice stream of a person, the system comprising;
a memory storing instructions; and
a processor that, when executing the instructions, is configured to:
retrieve user information for an identified user interacting with the voice stream output by the device;
determine, by a neural network, if the user information indicates help is needed for the identified user to understand the voice stream;
identify a change to be made to the voice stream output by the device based on retrieved user information;
change the voice stream output by the device, using a voice changer, as identified by the retrieved user information; and
provide a changed live voice stream output by the device to interact with the identified user.

13. The system of claim 12 , wherein the processor is further configured to:
receive feedback information from the identified user, the feedback information indicating difficulty the identified user has with understanding the live voice stream;
receive feedback information comprising body language information for the identified user; and
determine if the body language information signifies an inability to understand the live voice stream or a misunderstanding of the live voice stream.

14. The system of claim 12 , wherein the processor is further configured to detect a trend of volume in words spoken by the user as being increased or decreased, and the voice changer is configured to change the live voice stream to follow the trend of the volume.

15. The system of claim 12 , wherein the voice changer is configured to increase or decrease the trend of volume of words of the live voice stream in a manner similar to the trend of the volume of the words spoken by the user.

16. The system of claim 12 , wherein the processor is configured to:
retrieve voice frequency change information indicating a voice frequency change to make to frequency components of the live voice stream;
wherein the voice changer is configured to reduce a magnitude of the frequency components of the voice stream according to the voice frequency change information.

17. The system of claim 12 , wherein the processor is configured to:
retrieve intonation change information based on a preferred intonation pattern of the identified user indicating an intonation change to make to an intonation of the live voice stream.

18. The system of claim 12 , wherein the processor is configured to detect a trend of intonation being increased or decreased; and
wherein the voice changer increases or decreases the intonation of the live voice stream in a similar manner.

19. The method of claim 1 , wherein the live voice stream is remote.

20. The method of claim 1 , wherein the live voice stream is from a person talking to the user in person.

Assignees

• Capital One Services Llc

Inventors

• Truong Ahn
• Watson Mark
• Goodsitt Jeremy
• Pham Vincent
• Abdi Taghi Abad Fardin
• Key Kate
• Walters Austin
• Farivar Reza

Classifications

• G06V40/28

  Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113) · CPC title

• G06V40/174

  Facial expression recognition · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/82

  using neural networks · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title