PUBLIC SPEAKING SELF-EVALUATION TOOL

• US 20090089062A1
• Filed: 10/01/2007
• Published: 04/02/2009
• Est. Priority Date: 10/01/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lu, Fang
• Granted Patent: US 7,941,318 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G09B 5/04 with audible presentation of the material to be studied sound recording or reproducing G11B
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A public speaking self-evaluation tool that helps a user practice public speaking in terms of avoiding undesirable words or sounds, maintaining a desirable speech rhythm, and ensuring that the user is regularly glancing at the audience. The system provides a user interface through which the user is able to define the undesirable words or sounds that are to be avoided, as well as a maximum frequency of occurrence threshold to be used for providing warning signals based on detection of such filler or undesirable words or sounds. The user interface allows a user to define a speech rhythm, e.g. in terms of spoken syllables per minute, that is another maximum threshold for providing a visual warning indication. The disclosed system also provides a visual indication when the user fails to glance at the audience at least as often as defined by a predefined minimum threshold.

Claims

1. A method for helping a user practice public speaking, comprising:

inputting a user'"'"'s speech;

detecting, responsive to said input user'"'"'s speech, each occurrence of a sound in said user'"'"'s speech that matches at least one sound defined in a predetermined set of undesirable sounds;

responsive to each said detection of said each said occurrence of said sound in said user'"'"'s speech that matches at least one sound defined in said predetermined set of undesirable sounds, outputting an undesirable sound detected warning;

determining, responsive to said input user'"'"'s speech, a speech speed;

comparing said speech speed to a predetermined maximum speech speed threshold;

responsive to said speech speed exceeding said predetermined maximum speed threshold, outputting a speech speed exceeded warning;

inputting eye movements of said user;

responsive to said input eye movements of said user, determining when said user glances up and maintaining an audience glance frequency measurement indicating a frequency at which said user glances up;

comparing said audience glance frequency measurement with a predetermined minimum audience glance frequency threshold; and

responsive to said audience glance frequency measurement falling below said predetermined minimum audience glance frequency threshold, outputting an audience glance frequency threshold not met warning.

2. The method of claim 1, further comprising:

maintaining an undesirable sound frequency measurement indicating a frequency of occurrence of sounds in said user'"'"'s speech matching at least one sound defined in said predetermined set of undesirable sounds;

comparing said undesirable sound frequency measurement to a predetermined undesirable sound frequency threshold; and

responsive to said undesirable sound frequency measurement exceeding said undesirable sound frequency threshold, outputting an undesirable sound threshold exceeded warning.

3. The method of claim 2, wherein said inputting of said user'"'"'s speech includes receiving said user'"'"'s speech through a microphone in analog form, and storing a digital representation of said user'"'"'s speech in a system memory.

4. The method of claim 3, further comprising generating a user interface allowing said user to input said predetermined set of undesirable sounds.

5. The method of claim 4, wherein said undesirable sound detected warning comprises a first visual warning provided through said user interface.

6. The method of claim 5, wherein said user interface further allows said user to input said predetermined undesirable sound frequency threshold.

7. The method of claim 6, wherein said undesirable sound threshold exceeded warning comprises a second visual warning provided through said user interface.

8. The method of claim 7, wherein said speech speed comprises a syllable frequency in said input user'"'"'s speech.

9. The method of claim 8, wherein said user interface further allows said user to input said predetermined maximum speech speed threshold.

10. The method of claim 9, wherein said user interface allows said user to input said predetermined maximum speech speed threshold through a slider user interface display object.

11. The method of claim 10, wherein said user interface further includes a dynamically updated graph representation of said syllable frequency in said input user'"'"'s speech.

12. The method of claim 11, wherein said audience glance frequency threshold not met warning comprises a text warning displayed in said user interface.

13. A system for helping a user practice public speaking, comprising:

speech input circuitry for inputting a user'"'"'s speech;

undesirable sound detection logic for detecting, responsive to said input user'"'"'s speech, each occurrence of a sound in said user'"'"'s speech that matches at least one sound defined in a predetermined set of undesirable sounds;

undesirable sound detected warning output logic for, responsive to each said detection of said each said occurrence of said sound in said user'"'"'s speech that matches at least one sound defined in said predetermined set of undesirable sounds, outputting an undesirable sound detected warning;

speech speed determining logic for determining, responsive to said input user'"'"'s speech, a speech speed;

speech speed threshold comparison logic for comparing said speech speed to a predetermined maximum speech speed threshold;

speech speed threshold exceeded warning output logic for, responsive to said speech speed exceeding said predetermined maximum speed threshold, outputting a speech speed exceeded warning;

eye movement tracking circuitry for inputting eye movements of said user;

audience glance frequency determining logic for, responsive to said input eye movements of said user, determining when said user glances up and maintaining an audience glance frequency measurement indicating a frequency at which said user glances up;

audience glance comparison logic for comparing said audience glance frequency measurement with a predetermined minimum audience glance frequency threshold; and

audience glance frequency threshold not met warning output logic for, responsive to said audience glance frequency measurement falling below said predetermined minimum audience glance frequency threshold, outputting an audience glance frequency threshold not met warning.

14. A computer program product including a computer readable medium, said computer readable medium having program code for helping a user practice public speaking stored thereon, said program code comprising:

program code for detecting, responsive to input user'"'"'s speech, each occurrence of a sound in said user'"'"'s speech that matches at least one sound defined in a predetermined set of undesirable sounds;

program code for, responsive to each said detection of said each said occurrence of said sound in said user'"'"'s speech that matches at least one sound defined in said predetermined set of undesirable sounds, outputting an undesirable sound detected warning;

program code for determining, responsive to said input user'"'"'s speech, a speech speed;

program code for comparing said speech speed to a predetermined maximum speech speed threshold;

program code for, responsive to said speech speed exceeding said predetermined maximum speed threshold, outputting a speech speed exceeded warning;

program code for, responsive to input eye movements of said user, determining when said user glances up and maintaining an audience glance frequency measurement indicating a frequency at which said user glances up;

program code for comparing said audience glance frequency measurement with a predetermined minimum audience glance frequency threshold; and

program code for, responsive to said audience glance frequency measurement falling below said predetermined minimum audience glance frequency threshold, outputting an audience glance frequency threshold not met warning.

15. A computer data signal embodied in a carrier wave, said computer data signal have encoded thereon program code for helping a user practice public speaking stored thereon, said program code comprising:

program code for detecting, responsive to input user'"'"'s speech, each occurrence of a sound in said user'"'"'s speech that matches at least one sound defined in a predetermined set of undesirable sounds;

program code for, responsive to each said detection of said each said occurrence of said sound in said user'"'"'s speech that matches at least one sound defined in said predetermined set of undesirable sounds, outputting an undesirable sound detected warning;

program code for determining, responsive to said input user'"'"'s speech, a speech speed;

program code for comparing said speech speed to a predetermined maximum speech speed threshold;

program code for, responsive to said speech speed exceeding said predetermined maximum speed threshold, outputting a speech speed exceeded warning;

program code for, responsive to input eye movements of said user, determining when said user glances up and maintaining an audience glance frequency measurement indicating a frequency at which said user glances up;

program code for comparing said audience glance frequency measurement with a predetermined minimum audience glance frequency threshold; and

program code for, responsive to said audience glance frequency measurement falling below said predetermined minimum audience glance frequency threshold, outputting an audience glance frequency threshold not met warning.

16. A system for helping a user practice public speaking, comprising:

means for inputting a user'"'"'s speech;

means for detecting, responsive to said input user'"'"'s speech, each occurrence of a sound in said user'"'"'s speech that matches at least one sound defined in a predetermined set of undesirable sounds;

means, responsive to each said detection of said each said occurrence of said sound in said user'"'"'s speech that matches at least one sound defined in said predetermined set of undesirable sounds, for outputting an undesirable sound detected warning;

means for determining, responsive to said input user'"'"'s speech, a speech speed;

means for comparing said speech speed to a predetermined maximum speech speed threshold;

means, responsive to said speech speed exceeding said predetermined maximum speed threshold, for outputting a speech speed exceeded warning;

means for inputting eye movements of said user;

means, responsive to said input eye movements of said user, for determining when said user glances up and maintaining an audience glance frequency measurement indicating a frequency at which said user glances up;

means for comparing said audience glance frequency measurement with a predetermined minimum audience glance frequency threshold; and

means, responsive to said audience glance frequency measurement falling below said predetermined minimum audience glance frequency threshold, for outputting an audience glance frequency threshold not met warning.