Speaker intent analysis system

• US 20110066436A1
• Filed: 10/25/2010
• Published: 03/17/2011
• Est. Priority Date: 11/12/2002
• Status: Active Grant

• Current Assignee: Bezar Irrevocable Trust
• Original Assignee: Bezar Family Irrevocable Trust
• Inventors: Bezar, David
• Granted Patent: US 8,200,494 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A speaker intent analysis system and method for validating the truthfulness and intent of a plurality of participants'"'"' responses to questions. A computer stores, retrieves, and transmits a series of questions to be answered audibly by participants. The participants'"'"' answers are received by a data processor. The data processor analyzes and records the participants'"'"' speech parameters for determining the likelihood of dishonesty. In addition to analyzing participants'"'"' speech parameters for distinguishing stress or other abnormality, the processor may be equipped with voice recognition software to screen responses that while not dishonest, are indicative of possible malfeasance on the part of the participants. Once the responses are analyzed, the processor produces an output that is indicative of the participant'"'"'s credibility. The output may be sent to proper parties and/or devices such as a web page, computer, e-mail, PDA, pager, database, report, etc. for appropriate action.

Claims

1. A speaker intent analysis system comprising:

a. a plurality of participant transceivers, each including a transmitter for transmitting audible answers and receiver for receiving audible questions;

b. at least one “

inquiry”

transceiver including a transmitter for transmitting audible questions to said participant receivers and a receiver for receiving the audible answers to the questions;

c. a communications network for connecting said participant transceivers to said inquiry transceiver; and

d. a central voice processor connected to said communications network and said inquiry transceiver for receiving the audible answers from said questions, said central voice processor including capabilities of voice analysis including analyzing speech parameters of the plurality of audible answers for producing determinations as to a participant'"'"'s intent to deceive or not deceive when producing the audible answers.

2. The speaker intent analysis system of claim 1 wherein said inquiry transceiver includes a computer processor for automatically transmitting said questions from an internal database.

3. The speaker intent analysis system of claim 1 wherein said inquiry transceiver is constructed in the form of a traditional telephone to allow a person to verbally propound questions transmitted to said participant transceivers.

4. The speaker intent analysis system of claim 1 comprises a plurality of “

inquiry”

transceivers, said inquiry transceivers including a transmitter for transmitting questions to said participant receivers and a receiver for receiving the audible answers to the questions.

5. The speaker intent analysis system of claim 2 wherein said communications network is a telephone network.

6. The speaker intent analysis system of claim 4 wherein said communications network is a telephone network.

7. A method for assessing speaker intent comprising the steps of:

a. transmitting audible questions over a communications network to a plurality of participants at one time;

b. receiving audible answers to the questions by a central processor;

c. analyzing a plurality of participant audible answers by the central processor; and

d. producing a computer generated output reflecting a determination as to a participants'"'"' emotional states including the participants'"'"' intent to deceive or not deceive when producing their responses.

8. The method for assessing speaker intent of claim 7 further comprising the step of:

a. recognizing the identity of a participant using speech recognition software.

9. The method for assessing speaker intent of claim 8 further comprising the steps of:

a. providing a list of persons; and

b. producing an alert if the participant is identified as a person on a specified list.

10. A speaker intent analysis system comprising:

a. an inquiry transceiver including a first transmitter for transmitting audible questions to a plurality of participants to elicit a participants'"'"' audible answers and a first receiver for receiving the participants'"'"' audible answers;

b. a plurality of participant transceivers each participant transceiver including a second receiver for receiving the participant'"'"'s audible answers to the questions and a second transmitter for transmitting the participant'"'"'s audible answers;

c. a communications network for connecting said participant transceivers to the inquiry transceiver;

d. a database for containing questions; and

e. a computer processor connected to said communications network and said database, said computer processor retrieving questions from the database based on information gained from earlier participant audible answers, transmitting audible questions to the first transmitter for transmission to participants, receiving the participant'"'"'s audible answers from the first receiver, and analyzing the speech parameters of the audible answers for producing determinations as to a participant'"'"'s intent to deceive or not deceive when producing the responses.

11. A method for assessing speaker intent comprising the steps of:

a. retrieving questions stored on a memory medium using a computer;

b. transmitting the questions for audible production over a communications network to a plurality of participant transceivers using a computer;

c. receiving from the participant transceivers and analyzing the plurality of participants'"'"' audible answers to the audible questions to produce a computer generated determination as to a participant'"'"'s intent to deceive or not deceive when producing the responses; and

d. outputting a product of analysis for each participant indicative of the probability that the participant intended to deceive or not deceive when producing the participants'"'"' audible answers.

12. The method for assessing speaker intent of claim 11 further comprising the steps of:

a. recognizing a participant'"'"'s audible answers to a question by a voice-recognition process; and

b. outputting an alert if the participant'"'"'s audible answers meets a certain criteria.

13. The method for assessing speaker intent of claim 11 further comprising the step of:

a. recognizing the identity of a participant using speech recognition software.

14. The method for assessing speaker intent of claim 13 further comprising the steps of:

a. providing a list of persons; and

b. producing an alert if the participant is identified as a person on the list.

15. The method for assessing credibility of claim 11 further comprising the steps of:

a. simultaneously transmitting audible questions and receiving audible answers to and from a plurality of participants at one time.

16. The method for assessing credibility of claim 15 further comprising the step of:

a. processing audible answers from a plurality of participants at one time.

17. The method for assessing credibility of claim 11 further comprising the steps of:

a. transmitting audible questions over a communications network to a participant during a first session;

b. receiving the participant'"'"'s audible answers to the questions during the first session to obtain calibration data concerning the participant'"'"'s voice;

c. storing the calibration data for retrieval at a later time;

d. transmitting audible questions over a communications network to a participant during a second session;

e. receiving and comparing the participant'"'"'s audible answers from the second session to the calibration data to produce a computer generated determination of the credibility of the participant; and

f. outputting a product of analysis indicative of the probability that the participant has been truthful based on

18. The method for assessing speaker intent of claim 17 further comprising the steps of:

a. providing a list of persons; and

b. producing an alert if the participant is identified as a person on the list.

19. The method for assessing credibility of claim 17 further comprising the step of:

a. simultaneously transmitting audible questions and receiving audible answers to and from a plurality of participants at one time.

20. The method for assessing credibility of claim 17 further comprising the step of:

a. processing audible answers from a plurality of participants at one time to produce computer generated determinations of credibility of the plurality of participants.