Systems and methods for dynamically analyzing temporality in speech

• US 7,324,944 B2
• Filed: 12/11/2003
• Issued: 01/29/2008
• Est. Priority Date: 12/12/2002
• Status: Expired due to Fees

• Current Assignee: Technology Transfer Office Brigham Young University
• Original Assignee: Technology Transfer Office Brigham Young University
• Inventors: Hansen, Lynne, Rowe, Joshua
• Primary Examiner(s): CHAWAN, VIJAY B
• Application Number:
  US10/734,084
• Publication Number:
  US 20040193409A1
• Time in Patent Office: 1,510 Days
• Field of Search: 704270-278, 704/231, 704/251, 704/211, 434/178, 434/156, 434/157, 434/185
• US Class Current: 704/270
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G09B 7/02 of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
• 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 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34

Abstract

Systems and methods for dynamically analyzing temporality in an individual'"'"'s speech in order to selectively categorize the speech fluency of the individual and/or to selectively provide speech training based on the results of the dynamic analysis. Temporal variables in one or more speech samples are dynamically quantified. The temporal variables in combination with a dynamic process, which is derived from analyses of temporality in the speech of native speakers and language learners, are used to provide a fluency score that identifies a proficiency of the individual. In some implementations, temporal variables are measured instantaneously.

Claims

1. A method for determining speech fluency, the method comprising:

obtaining one or more speech samples from an individual;

identifying variables present in the speech samples;

obtaining an average length of speech run by the individual;

obtaining an average length of silent pause by the individual;

measuring a total amount of silent time by the individual;

measuring a total amount of speech time by the individual;

measuring a total number of speech runs by the individual;

dynamically analyzing and selectively weighting the variables to determine a speech fluency score;

comparing the speech fluency score with established fluency ranges; and

indicating a speech fluency of the individual based on the dynamic analysis, weighting, and comparison.

2. A method as recited in claim 1, further comprising measuring a total number of silent pauses by the individual.

3. A method as recited in claim 1, wherein obtaining one or more speech samples comprises recording the one or more speech samples in an electronic format.

4. A method as recited in claim 3, wherein the electronic format is a .wav format.

5. A method as recited in claim 1, wherein dynamically analyzing and selectively weighting the variables comprises using a computer device to perform at least a portion of the dynamic analysis and weighting.

6. A method as recited in claim 5, wherein dynamically analyzing and selectively weighting the variables includes automatically measuring the variables in the speech samples.

7. A method as recited in claim 6, wherein the variables are measured instantaneously.

8. A method as recited in claim 1, wherein dynamically analyzing and selectively weighting the variables includes weighting the variables based on relevance.

9. A computer program product for implementing within a computer system a method for determining speech fluency, the computer program product comprising:

a computer readable medium for providing computer program code means utilized to implement the method, wherein the computer program code means is comprised of executable code for implementing;

receiving one or more speech samples of an individual;

identifying variables present in the speech samples;

obtaining an average length of speech run by the individual;

obtaining an average length of silent pause by the individual;

measuring a total amount of silent time by the individual;

measuring a total amount of speech time by the individual;

measuring a total number of speech runs by the individual;

dynamically analyzing and selectively weighting the variables to determine a speech fluency score;

comparing the speech fluency score with established fluency ranges; and

indicating the speech fluency of the individual based on the dynamic analysis, weighting and comparison.

10. A computer program product as recited in claim 9, wherein the computer program code means is further comprised of executable code for implementing measuring a total number of silent pauses by the individual.

11. A computer program product as recited in claim 9, wherein receiving one or more speech samples comprises recording the one or more speech samples in an electronic format.

12. A computer program product as recited in claim 11, wherein the electronic format is a .wav format.

13. A computer program product as recited in claim 9, wherein dynamically analyzing and selectively weighting the variables includes electronically measuring the variables in the speech samples.

14. A computer program product as recited in claim 13, wherein the temporal variables are measured instantaneously.

15. A computer program product as recited in claim 9, wherein dynamically analyzing and selectively weighting the variables includes selectively weighting the variables based on relevance.