Method of and system for providing adaptive respondent training in a speech recognition application

• US 10,522,144 B2
• Filed: 03/05/2018
• Issued: 12/31/2019
• Est. Priority Date: 10/16/2000
• Status: Expired due to Term

• Current Assignee: Eliza Corporation (Gainwell Technologies)
• Original Assignee: Eliza Corporation (Gainwell Technologies)
• Inventors: Quibria, Nasreen, Merrow, Lucas, Boulanov, Oleg, Kroeker, John P., Drane, Alexandra
• Primary Examiner(s): Vo, Huyen X
• Application Number:
  US15/911,965
• Publication Number:
  US 20180197541A1
• Time in Patent Office: 666 Days
• Field of Search: 704230-257, 704270-275
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: G10L 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34
• CPC Class Codes: G10L 25/03 characterised by the type of extracted parameters
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2016 Call initiation by network rather than by subscriber
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/382 using authorisation codes or passwords
• CPC Class Codes: H04M 3/46 Arrangements for calling a number of substations in a predetermined sequence until an answer is obtained
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5158 in combination with automated outdialling systems devices for signalling identity of wanted subscriber H04M1/26
• CPC Class Codes: H04M 3/523 with call distribution or queueing

Abstract

A system for conducting a telephonic speech recognition application includes an automated telephone device for making telephonic contact with a respondent and a speech recognition device which, upon the telephonic contact being made, presents the respondent with at least one introductory prompt for the respondent to reply to; receives a spoken response from the respondent; and performs a speech recognition analysis on the spoken response to determine a capability of the respondent to complete the application. If the speech recognition device, based on the spoken response to the introductory prompt, determines that the respondent is capable of competing the application, the speech recognition device presents at least one application prompt to the respondent. If the speech recognition device, based on the spoken response to the introductory prompt, determines that the respondent is not capable of completing the application, the speech recognition system presents instructions on completing the application to the respondent.

Claims

1. A method of conducting an automatic telephonic speech recognition application comprising:

initiating, with the automatic telephonic speech recognition application, a telephone call with a respondent;

producing, with the automatic telephonic speech recognition application, at least one introductory auditory prompt, the at least one introductory auditory prompt requesting an auditory response from the respondent;

analyzing, with a speech recognition algorithm, the auditory response provided by the respondent;

determining an interaction capability of the respondent based on the analyzed auditory response;

providing, with the automatic telephonic speech recognition application and based on the interaction capability of the respondent, the respondent with at least one auditory prompt associated with an application, including an explanation of an operation of the automatic telephonic speech recognition application, the explanation being based on the interaction capability of the respondent and enabling the respondent to provide an auditory response to the at least one auditory prompt associated with the application; and

prompting, in response to the explanation of the operation of the speech recognition application, the respondent to confirm understanding of the explanation via a query.

2. The method of claim 1 wherein the explanation includes at least one of a sample prompt, demonstration, or instruction.

3. The method of claim 1, wherein the interaction capability of the respondent is determined by a compatible auditory response.

4. The method of claim 3, wherein the compatible auditory response is an acceptable value from a plurality of acceptable values.

5. The method of claim 3, wherein the compatible auditory response is in a predetermined format.

6. The method of claim 1, further comprising:

providing, in response to the explanation of the operation of the speech recognition application, a training exercise for the respondent.

7. The method of claim 1, wherein the introductory auditory prompt is about one of a product, service, person, department, or opinion.

8. The method of claim 1, further comprising:

asking, with the automatic telephonic speech recognition application, an identity of the respondent; and

verifying, with the automatic telephonic speech recognition application, the identity of the respondent.

9. The method of claim 1, further comprising:

storing in a database, by the automated telephonic speech recognition application, a user response to the at least one auditory prompt associated with an application.

10. A system for conducting an automatic telephonic speech recognition application comprising:

an automated telephone device for initiating a telephone call with a respondent; and

a speech recognition device configured to, upon the telephone call being initiated, present the respondent with at least one introductory auditory prompt requesting an auditory response from the respondent;

receive the auditory response from the respondent; and

perform a speech recognition analysis on the auditory response to determine an interaction capability of the respondent to complete the application;

wherein, the speech recognition device upon a determination, based on the auditory response to the introductory auditory prompt, that the respondent is capable of completing the application, is configured to present at least one application auditory prompt to the respondent; and

wherein, the speech recognition device upon a determination, based on the auditory response to the introductory auditory prompt, that the respondent is not capable of completing the application, is configured to present an explanation to the respondent, the explanation being based on the interaction capability of the respondent and enabling the respondent to provide an auditory response to the at least one application auditory prompt associated with the application,

wherein the speech recognition device is further configured to prompt, in response to the explanation on completing the application, the respondent to confirm understanding of the explanation via a query.

11. The system of claim 10 wherein the explanation includes at least one of a sample prompt, demonstration, or instruction.

12. The system of claim 10, wherein the interaction capability of the respondent is determined by a compatible auditory response.

13. The system of claim 12, wherein the compatible auditory response is an acceptable value from a plurality of acceptable values.

14. The system of claim 12, wherein the compatible auditory response is in a predetermined format.

15. The system of claim 10, wherein the speech recognition device is configured to provide, in response to the explanation on completing the application, a training exercise for the respondent.

16. The system of claim 10, wherein the introductory auditory prompt is about one of a product, service, person, department, or opinion.

17. The system of claim 10, wherein the speech recognition device is further configured to ask for an identity of the respondent;

and verify the identity of the respondent upon receiving the identity from the respondent.

18. The system of claim 10, further including a dataset, and wherein the speech recognition device is configured to store a user response to the at least one application auditory prompt in the database.