System and method for customized voice response

• US 10,192,547 B2
• Filed: 04/21/2016
• Issued: 01/29/2019
• Est. Priority Date: 06/18/2010
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group), Kia Corp.
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Duffield, Nicholas
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US15/135,237
• Publication Number:
  US 20160240191A1
• Time in Patent Office: 1,013 Days
• Field of Search: 704231, 704236, 704251, 704254, 704 2, 704 9, 704275, 379 8801
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/14 Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 2203/255 comprising a personalized user interface
• CPC Class Codes: H04M 2250/58 including a multilanguage function
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for approximating an accent source. A system practicing the method collects data associated with customer specific services, generates country-specific or dialect-specific weights for each service in the customer specific services list, generates a summary weight based on an aggregation of the country-specific or dialect-specific weights, and sets an interactive voice response system language model based on the summary weight and the country-specific or dialect-specific weights. The interactive voice response system can also change the user interface based on the interactive voice response system language model. The interactive voice response system can tune a voice recognition algorithm based on the summary weight and the country-specific weights. The interactive voice response system can adjust phoneme matching in the language model based on a possibility that the speaker is using other languages.

Claims

1. A method comprising:

analyzing, by a system comprising a processor, human interactions between a user and each of a plurality of network services to generate a respective country-specific weight associated with each respective network service of the plurality of network services to yield country-specific weights, each respective country-specific weight representing a probability that a language specific to a corresponding country is identified in the human interactions, wherein data associated with the human interactions between the user and each of the plurality of network services is recorded in at least two of a phone record, an internet services record, and a content viewing record to yield recorded data;

aggregating, by the system and based at least in part on the recorded data, the country-specific weights to generate summary weights;

selecting, by the system, a language model based on the summary weights; and

recognizing, by the system, speech received from a device associated with the user by applying the language model to the speech in an interactive voice response system.

2. The method of claim 1, wherein the processor comprises a plurality of processors operating in a distributed processing environment, and further comprising collecting human interaction information according to a customer-specific list of the plurality of network services associated with the user.

3. The method of claim 1, wherein the system changes a user interface based on the language model.

4. The method of claim 1, wherein the interactive voice response system selects language options for a splash screen based on the country-specific weights.

5. The method of claim 1, wherein the interactive voice response system tunes a voice recognition algorithm based on the country-specific weights.

6. The method of claim 1, wherein the interactive voice response system adjusts phoneme matching in the language model based on a probability that the user is using other languages based on the country-specific weights.

7. The method of claim 1, wherein the interactive voice response system monitors a number of times the user repeats speech input.

8. The method of claim 1, wherein the internet service record includes a user requested top level domain, a web page language encoding, a browsing history, a viewed web page content, or any combination thereof.

9. The method of claim 1, wherein the content viewing record comprises one or more of a viewing history, a time of channel changes, a content of viewed channels, a digital video recorder recording history, scheduled shows for recording, a viewing location, or any combination thereof.

10. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

analyzing human interactions between a user and each of a plurality of network services to generate a respective country-specific weight associated with each respective network service to yield country-specific weights, each respective country-specific weight representing a probability that a language specific to a corresponding country is identified in the human interactions, wherein data associated with the human interactions between the user and each of the plurality of network services is recorded in at least two of a phone record, an internet services record, and a content viewing record to yield recorded data;

aggregating, based at least in part on the recorded data, the country-specific weights to generate summary weights;

selecting, based at least in part on the recorded data, a language model based on the summary weights; and

recognizing speech received from a device associated with the user by applying the language model to the speech in an interactive voice response system.

11. The non-transitory machine-readable storage medium of claim 10, wherein the processor comprises a plurality of processors operating in a distributed processing environment, and wherein the operations further comprise determining the plurality of network services according to a customer-specific list of network services that are associated with the user.

12. The non-transitory machine-readable storage medium of claim 10, wherein the interactive voice response system adjusts a user interface based on the language model.

13. The non-transitory machine-readable storage medium of claim 10, wherein the interactive voice response system selects language options for a splash screen based on the country-specific weights.

14. The non-transitory machine-readable storage medium of claim 10, wherein the interactive voice response system tunes a voice recognition algorithm based on the country-specific weights.

15. The non-transitory machine-readable storage medium of claim 10, wherein the interactive voice response system adjusts phoneme matching in the language model based on a probability that the user is using other languages based on the country-specific weights.

16. The non-transitory machine-readable storage medium of claim 10, wherein the interactive voice response system monitors a number of times the user repeats speech input.

17. A device, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

analyzing human interactions between a user and each of a plurality of network services to generate a respective country-specific weight associated with each respective network service of the plurality of network services to yield country-specific weights, each respective country-specific weight representing a probability that a language specific to a corresponding country is identified in the human interactions, wherein data associated with the human interactions between the user and each of the plurality of network services is recorded in at least two of a phone record, an internet services record, and a content viewing record to yield recorded data;

aggregating, based at least in part on the recorded data, the country-specific weights to generate summary weights;

selecting, based at least in part on the recorded data, a language model based on the summary weights; and

recognizing, via an interactive voice response system implementing the language model, speech received from a device associated with the user.

18. The device of claim 17, wherein the processor comprises a plurality of processors operating in a distributed processing environment.