Voice Detection For Automated Communication System

• US 20130204607A1
• Filed: 03/15/2013
• Published: 08/08/2013
• Est. Priority Date: 12/08/2011
• Status: Active Grant

• Current Assignee: Noguar Lc
• Original Assignee: Forrest S Baker III Trust
• Inventors: Baker, Forrest IV
• Granted Patent: US 9,583,108 B2
• Time in Patent Office: Days
• US Class Current: 704/8
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

A system implements voice detection using a receiver, a voice analyzer, and a voice identifier. The receiver receives a transmission from a transmission channel associated with a channel identification. The transmission includes a voice input. The voice analyzer analyzes the voice input and generates a plurality of voice metrics according to a plurality of analysis parameters. The voice identifier compares the voice metrics to one or more stored sets of voice metrics. Each set of voice metrics corresponds to a voice identification associated with the channel identification. The voice identifier also identifies a match between the voice metrics from the voice analyzer and at least one of the stored sets of voice metrics.

Claims

1. A system comprising:

a receiver to receive a transmission from a transmission channel associated with a channel identification, wherein the transmission comprises a voice input;

a voice analyzer coupled to the receiver, wherein the voice analyzer is configured to analyze the voice input and to generate a plurality of voice metrics according to a plurality of analysis parameters; and

a voice identifier coupled to the voice analyzer, wherein the voice identifier is configured to compare the voice metrics to one or more stored sets of voice metrics, wherein each set of voice metrics corresponds to a voice identification associated with the channel identification, and the voice identifier is further configured to identify a match between the voice metrics from the voice analyzer and at least one of the stored sets of voice metrics.

2. The system of claim 1, wherein the voice analyzer comprises a fast Fourier transform (FFT) engine, wherein the FFT engine is configured to generate a FFT spectrum analysis of the voice input, wherein the FFT spectrum analysis comprises a plurality of frequency bands from the voice input.

3. The system of claim 1, wherein the voice analyzer comprises a word boundary engine, wherein the word boundary engine is configured to identify a start boundary and an end boundary for a word within the voice input based on corresponding time periods preceding and following sounds determined to be the word.

4. The system of claim 3, wherein the voice analyzer is further configured to generate the plurality of voice metrics for each word identified by the word boundary engine.

5. The system of claim 3, wherein the voice analyzer further comprises a word splitter engine, wherein the word splitter engine is configured to split the word identified by the word boundary engine into a plurality of word segments.

6. The system of claim 5, wherein the voice analyzer is further configured to generate the plurality of voice metrics for each word segment identified by the word splitter engine.

7. The system of claim 1, wherein the voice analyzer comprises a segment length engine, wherein the segment length engine is configured to generate voice metrics descriptive of a length of a segment of a frequency band.

8. The system of claim 7, wherein the segment corresponds to a word within the voice input.

9. The system of claim 1, wherein the voice analyzer comprises a frequency crossing engine, wherein the frequency crossing engine is configured to generate voice metrics descriptive of a count of signal crossings within a segment of a frequency band.

10. The system of claim 1, wherein the voice analyzer comprises an angularity engine, wherein the angularity engine is configured to generate voice metrics descriptive of an angular slope of a portion of a frequency signal within a segment of a frequency band.

11. A method comprising:

establishing a verbal communication session on a communication channel between at least two communication participants;

identifying a channel identification for the communication channel;

identifying a first communication participant of the at least two communication participants from a set of potential communication participants associated with the channel identification; and

electronically modifying a script presented to a second communication participant of the at least two communication participants in response to identifying the first communication participant, wherein the script comprises language prompts for the second communication participant to communicate to the first communication participant during the verbal communication session.

12. The method of claim 11, wherein identifying the first communication participant further comprises:

digitally analyzing a voice input from the first communication participant to generate a plurality of voice metrics according to a plurality of analysis parameters;

comparing the generated voice metrics to one or more stored sets of voice metrics, wherein each set of voice metrics corresponds to a voice identification associated with the channel identification; and

identifying a match between the generated voice metrics and at least one of the stored sets of voice metrics.

13. The method of claim 12, wherein digitally analyzing the voice input from the first communication participant comprises generating a FFT spectrum analysis of the voice input, wherein the FFT spectrum analysis comprises a plurality of frequency bands from the voice input.

14. The method of claim 12, wherein digitally analyzing the voice input from the first communication participant comprises identifying a start boundary and an end boundary for a word within the voice input based on corresponding time periods preceding and following sounds determined to be the word.

15. The method of claim 14, further comprising generating the plurality of voice metrics for each identified word.

16. The method of claim 14, further comprising:

splitting an identified word into a plurality of word segments; and

generating the plurality of voice metrics for each word segment.

17. The method of claim 12, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of a length of a segment of a frequency band.

18. The method of claim 12, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of a count of signal crossings within a segment of a frequency band.

19. The method of claim 12, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of an angular slope of a portion of a frequency signal within a segment of a frequency band.

20. The method of claim 12, further comprising:

comparing the voice metrics for the first communication participant to voice metrics of a plurality of other historical communication participants;

identifying a match between the voice metrics for the first communication participant and the voice metrics of at least one of the plurality of historical communication participants based on a comparison threshold; and

modifying the script presented to the second communication participant based on at least one historical script associated with the at least one historical communication participant whose associated voice metrics match the voice metrics for the first communication participant.

21. The method of claim 11, further comprising:

accessing demographic information about the first communication participant in response to identifying the first communication participant; and

modifying the script presented to the second communication participant in response to the demographic information associated with the first communication participant.

22. A method comprising:

monitoring verbal communications within a verbal communication session between a plurality of communication participants;

electronically comparing a flow of the verbal communications within the verbal communication session to a plurality of historical verbal communications stored in an electronic storage device;

determining that the flow of the verbal communications within the verbal communication session is compatible with at least one of the plurality of historical verbal communications;

deriving at least one script prompt from the at least one of the plurality of historical verbal communications with which the flow of the verbal communications within the verbal communication session is determined to be compatible; and

electronically providing the derived script prompt to a first communication participant of the plurality of communication participants during the verbal communication session.

23. The method of claim 22, further comprises identifying a trigger event while monitoring the verbal communications within the verbal communication session.

24. The method of claim 23, further comprising electronically comparing the flow of the verbal communications within the verbal communication session to the plurality of historical verbal communications in response to the trigger event.

25. The method of claim 23, further comprising postponing the electronically providing the derived script prompt to the first communication participant until after a threshold number of trigger events are identified.

26. The method of claim 23, further comprising:

electronically analyzing a voice input of the first communication participant; and

identifying the trigger event from the voice input of the first communication participant.

27. The method of claim 23, further comprising:

electronically analyzing a voice input of second communication participant other than the first communication participant; and

identifying the trigger event from the voice input of the second communication participant.

28. The method of claim 23, further comprising:

electronically analyzing a combination of voice inputs from the plurality of communication participants; and

identifying the trigger event from the combination of voice inputs from the plurality of communication participants.

29. A computer program product comprising:

a computer readable storage medium storing instructions thereon which, when executed by a computer processing device, cause the computer processing device to perform operations, wherein the operations comprise;

establishing a verbal communication session on a communication channel between at least two communication participants;

identifying a channel identification for the communication channel;

identifying a first communication participant of the at least two communication participants from a set of potential communication participants associated with the channel identification; and

electronically modifying a script presented to a second communication participant of the at least two communication participants in response to identifying the first communication participant, wherein the script comprises language prompts for the second communication participant to communicate to the first communication participant during the verbal communication session.

30. The computer program product of claim 29, wherein identifying the first communication participant further comprises:

digitally analyzing a voice input from the first communication participant to generate a plurality of voice metrics according to a plurality of analysis parameters;

comparing the generated voice metrics to one or more stored sets of voice metrics, wherein each set of voice metrics corresponds to a voice identification associated with the channel identification; and

identifying a match between the generated voice metrics and at least one of the stored sets of voice metrics.

31. The computer program product of claim 30, wherein digitally analyzing the voice input from the first communication participant comprises generating a FFT spectrum analysis of the voice input, wherein the FFT spectrum analysis comprises a plurality of frequency bands from the voice input.

32. The computer program product of claim 30, wherein digitally analyzing the voice input from the first communication participant comprises identifying a start boundary and an end boundary for a word within the voice input based on corresponding time periods preceding and following sounds determined to be the word.

33. The computer program product of claim 32, further comprising operations for generating the plurality of voice metrics for each identified word.

34. The computer program product of claim 32, further comprising operations for:

splitting an identified word into a plurality of word segments; and

generating the plurality of voice metrics for each word segment.

35. The computer program product of claim 30, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of a length of a segment of a frequency band.

36. The computer program product of claim 30, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of a count of signal crossings within a segment of a frequency band.

37. The computer program product of claim 30, wherein digitally analyzing the voice input from the first communication participant comprises generating voice metrics descriptive of an angular slope of a portion of a frequency signal within a segment of a frequency band.

38. The computer program product of claim 30, further comprising operations for:

comparing the voice metrics for the first communication participant to voice metrics of a plurality of other historical communication participants;

identifying a match between the voice metrics for the first communication participant and the voice metrics of at least one of the plurality of historical communication participants based on a comparison threshold; and

modifying the script presented to the second communication participant based on at least one historical script associated with the at least one historical communication participant whose associated voice metrics match the voice metrics for the first communication participant.

39. The computer program product of claim 29, further comprising operations for:

accessing demographic information about the first communication participant in response to identifying the first communication participant; and

modifying the script presented to the second communication participant in response to the demographic information associated with the first communication participant.