IP Library › Granted Patent US 10,522,169

Granted Patent B2

US 10,522,169 · App. 15/699,794 · Granted Dec 31, 2019

Classification of teaching based upon sound amplitude

Inventors: Kimberly Tanner (San Francisco, CA); Melinda T. Owens (San Mateo, CA); Jeffrey Schinske (San Francisco, CA); Mike Wong (San Francisco, CA); Shannon Seidel (Tacoma, WA)

Assignee: TRUSTEES OF THE CALIFORNIA STATE UNIVERSITY

G10L25/78 G09B19/00 G10L25/21 G10L25/48 G10L21/10

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 10,522,169
App. No.: 15/699,794
Granted: Dec 31, 2019
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A system is provided to determine teaching technique based upon sound amplitude comprising: processor; and a memory device holding an instruction set executable on the processor to cause the computer system to perform operations comprising: sampling amplitude of sound at a sampling rate; assigning a respective sound amplitude and a respective amplitude variation to the respective sound sample; and classifying the sound samples based upon the assigned sound amplitude and sound sample variation.

Claims (104)

1. A system to determine teaching technique based upon sound amplitude comprising:

a processor; and

a memory device holding an instruction set executable on the processor to cause the computer system to perform operations comprising:

storing in a storage memory device, a sequence of detected sound amplitude values representing sound amplitude emanating from a learning session during a corresponding sequence of time intervals;

producing a sequence of respective sound samples corresponding to the sequence of detected amplitude values by,

determining respective normalized sound amplitude values based upon respective detected sound amplitude values corresponding to respective time intervals within respective time windows, each respective time window having a prescribed number of time intervals and each respective time window encompassing a different collection of successive time intervals from the sequence of time intervals, and

determining respective variation values corresponding respective sound amplitude values based upon respective sound amplitude values corresponding to respective time intervals within respective time windows; and

classifying respective sound samples of the sequence of sound samples based upon the respective normalized stored amplitudes and the respective variation values of stored amplitude values.

2. The system of claim 1 ,

wherein determining respective normalized sound amplitude values based upon respective detected sound amplitude values corresponding to respective time intervals within respective time windows includes averaging respective detected sound amplitude values corresponding to respective time intervals within respective time windows.

3. The system of claim 1 ,

wherein determining respective normalized sound amplitude values based upon respective detected sound amplitude values corresponding to respective time intervals within respective time windows includes summing respective detected sound amplitude values corresponding to respective time intervals within respective time windows.

4. The system of claim 1 ,

wherein determining respective variation values corresponding to respective sound amplitude values corresponding to respective time intervals within respective time windows includes determining, based upon the detected sound amplitude values.

5. The system of claim 1 ,

6. The system of claim 1 ,

7. The system of claim 1 further including:

associating in a storage memory device, respective normalized sound amplitude values and respective variation values corresponding to respective sound amplitude values that correspond to respective common time intervals within respective common time windows.

8. The system of claim 1 further including:

a transducer to detect sound amplitude and to convert the sound amplitude and to an electrical signal having a value representing the detected sound amplitude.

9. The system of claim 1 ,

wherein storing includes storing at a sampling rate slow enough to not record details human speech.

10. The system of claim 1 ,

wherein the memory device the instruction set executable on the processor to further cause the computer system to perform operations comprising:

cutting out a range of detected sound amplitude values at a beginning and of a sequence of detected sound amplitude values and at an end of the sequence of detected sound amplitude values.

11. The system of claim 1 ,

wherein the memory device the instruction set executable on the processor to further cause the computer system to perform operations comprising:

normalizing respective detected sound amplitude values across a portion of a sample session that includes multiple respective time windows.

12. The system of claim 1 ,

wherein the memory device the instruction set executable on the processor to further cause the computer system to perform operations comprising:

normalizing sample variation across a portion of a sample session that includes multiple respective time windows.

13. The system of claim 1

wherein classifying the sound samples includes determining whether a respective sample has a combination of an assigned amplitude value and an assigned amplitude variation value that matches one of single voice classification parameter values, multiple voice parameter values, and no voice parameter values.

14. The system of claim 1 ,

wherein classifying the sound samples includes first determining whether a respective sample has a combination of an assigned amplitude value and an assigned amplitude variation value that matches a single voice classification parameter values; and

in response to determining that the respective sample has a combination of an assigned amplitude value and an assigned amplitude variation value that does not match a single voice classification parameter values, determining whether the respective sample has a combination of an assigned amplitude value and an assigned amplitude variation value that one of multiple voice parameter values and no voice parameter values.

15. The system of claim 1 ,

wherein the memory device the instruction set executable on the processor to further cause the computer system to perform operations comprising:

storing a single voice classification look up table;

storing a multiple voice classification look up table; and

storing a no voice classification look up table;

wherein classifying the sound samples based upon the assigned sound amplitude and sound sample variation includes comparing combinations of assigned sound amplitude and assigned sound variation with combinations of amplitude and variation stored in at least one of the single voice classification table, the multiple voice classification table, and the no voice classification table.

16. The system of claim 1 further including:

a display screen configured to display a chart indicating classification of samples within a sampling sequence.

17. A system to determine teaching technique based upon sound amplitude comprising:

means for producing a sequence of respective sound samples corresponding to the sequence of detected amplitude values by,

means for classifying respective sound samples of the sequence of sound samples based upon the respective normalized stored amplitudes and the respective variation values of stored amplitude values.

18. The system of claim 17 ,

wherein the means for classifying includes,

a single voice classification look up table;

a multiple voice classification look up tables; and

a no voice classification look up table.

19. The system of claim 17 further including:

means for cutting out a range of detected sound amplitude values at a beginning and of a sample sequence at an end of the sample sequence.

20. The system of claim 17 further including:

means for normalizing respective detected amplitude values across a portion of a sample session that includes multiple respective time windows.

21. A method to determine learning technique used within a learning session setting based upon sound amplitude, while protecting anonymity of instructors and students comprising:

detecting sound amplification sample values from electrical signals at a sampling rate that is low enough to anonymize the sound represented by the detected sound amplification sample values;

producing a sequence of respective sound samples corresponding to the sequence of detected amplitude values by,

classifying respective sound samples of the sequence of sound samples based upon the respective normalized stored amplitudes and the respective variation values of stored amplitude values.

22. The method of claim 21 ,

23. The method of claim 21 ,

24. The method of claim 21 further including:

storing a single voice classification look up table;

storing a multiple voice classification look up table; and

storing a no voice classification look up table;

25. A non-transitory machine-readable medium storing executable instructions thereon, which, when executed by a processor, cause the processor to perform operations including:

detecting sound amplification sample values from electrical signals, produced by a sound transducer, at a sampling rate that is low enough to anonymize sound represented by the detected sound amplification sample values;

producing a sequence of respective sound samples corresponding to the sequence of detected amplitude values by,

classifying respective sound samples of the sequence of sound samples based upon the respective normalized stored amplitudes and the respective variation values of stored amplitude values.

26. The method of claim 21 ,

wherein detecting includes storing at a sampling rate that is low enough so that individual voices cannot be recognized based upon the samples.

27. The method of claim 21 ,

wherein detecting includes storing at a sampling rate that is low enough so that individual words cannot be recognized based upon the samples.

28. The method of claim 21 ,

wherein detecting includes storing at a sampling rate that is 2 Hz.

29. The method of claim 21 further including:

converting by a sound transducer, sounds emanating from the learning session to produce the electrical signals, wherein the electrical signals have amplitude values indicative of sound amplitude during the session.

30. The method of claim 21 further including:

displaying on a display screen a chart indicating classification of samples within a sampling sequence.

31. The method of claim 21 further including:

displaying on a display screen one or more charts display segments indicating example sample activity footprints from different class sessions.

32. The method of claim 25 ,

wherein detecting includes storing at a sampling rate that is low enough so that individual voices cannot be recognized based upon the samples.

33. The method of claim 25 ,

wherein detecting includes storing at a sampling rate that is low enough so that individual words cannot be recognized based upon the samples.

34. The method of claim 25 ,

wherein detecting includes storing at a sampling rate that is 2 Hz.

35. The non-transitory machine-readable medium of claim 25 , the operations further including:

displaying on a display screen one or more chart display segments indicating example sample activity footprints from different class sessions.

36. The non-transitory machine-readable medium of claim 25 , the operations further including:

displaying on a display screen one or more charts display segments indicating example sample activity footprints from different class sessions.

Assignments (2)

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 24, 2019

From: TANNER, KIMBERLY; OWENS, MELINDA T.; SCHINSKE, JEFFREY; WONG, MIKE; SEIDEL, SHANNON

To: TRUSTEES OF THE CALIFORNIA STATE UNIVERSITY

Reel/Frame 049847/0916 →

CONFIRMATORY LICENSE Recorded May 29, 2019

From: SAN FRANCISCO STATE UNIVERSITY

To: NATIONAL SCIENCE FOUNDATION

Reel/Frame 049301/0036 →

Continuity (2)

Provisional Application 62398888 · Sep 23, 2016

Related Publication 20180090157A1 · Mar 29, 2018

Cited By (1)

US 12,400,658