User intent analysis extent of speaker intent analysis system

• US 8,972,266 B2
• Filed: 06/12/2012
• Issued: 03/03/2015
• Est. Priority Date: 11/12/2002
• Status: Active Grant

• Current Assignee: David Bezar
• Original Assignee: David Bezar
• Inventors: Bezar, David
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US13/494,771
• Publication Number:
  US 20120262296A1
• Time in Patent Office: 994 Days
• Field of Search: 704/246, 704/273, 704/270, 704/231, 704/247, 704/251, 704/255, 704/257, 704/272, 704/250, 434/350
• US Class Current: 704/273
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/56 Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities video conference systems H04N7/15

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, said participant transceivers including a transmitter for transmitting audible answers and a receiver for receiving audible questions, and said participant transceivers including a camera for capturing a facial image of a participant;

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 and for receiving facial images from said camera;

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

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

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 facial image analysis further including analysis including facial recognition to determine the identity of a participant.

4. The speaker intent analysis system of claim 3 further comprising

a. a list of persons;

and

b. alert means for producing an alert if a participant is identified as a person on said specified list.

5. 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;

d. obtaining a facial image of a participant;

e. analyzing the facial image of a participant by the central processor; and

f. producing a computer generated output reflecting a determination as to a participants'"'"' intent to deceive or not deceive based upon the participant'"'"'s facial image and their audible answers.

6. The method for assessing speaker intent of claim 5 further comprising the step of:

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

7. The method for assessing speaker intent of claim 6 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.

8. 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, said participant transceivers further including a camera for capturing a facial image of the participant;

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, said central processor also receiving and analyzing said participant facial images for producing a determination as to a participant'"'"'s identity.