Systems and Methods for an Automated Pronunciation Assessment System for Similar Vowel Pairs

• US 20140195239A1
• Filed: 01/07/2014
• Published: 07/10/2014
• Est. Priority Date: 01/07/2013
• Status: Active Grant

• Current Assignee: Educational Testing Service
• Original Assignee: Educational Testing Service
• Inventors: Evanini, Keelan
• Granted Patent: US 9,489,864 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G09B 5/06 with both visual and audible presentation of the material to be studied
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 25/15 the extracted parameters being formant information
• CPC Class Codes: G10L 25/60 for measuring the quality of voice signals

Abstract

Computer-implemented systems and methods are provided for assessing non-native speech proficiency. a non-native speech sample is processed to identify a plurality of vowel sound boundaries in the non-native speech sample. Portions of the non-native speech sample are analyzed within the vowel sound boundaries to extract vowel characteristics associated with a first vowel sound and a second vowel sound represented in the non-native speech sample. The vowel characteristics are processed to identify a first vowel pronunciation metric for the first vowel sound and a second vowel pronunciation metric for the second vowel sound, and the first vowel pronunciation metric and the second vowel pronunciation metric are processed to determine whether the non-native speech sample exhibits a distinction in pronunciation of the first vowel sound and the second vowel sound.

Claims

1. A computer-implemented method of assessing non-native speech proficiency, comprising:

processing, using a processing system, a non-native speech sample to identify a plurality of vowel sound boundaries in the non-native speech sample;

analyzing, using the processing system, portions of the non-native speech sample within the vowel sound boundaries to extract vowel characteristics associated with a first vowel sound and a second vowel sound represented in the non-native speech sample;

processing, using the processing system, the vowel characteristics to identify a first vowel pronunciation metric for the first vowel sound and a second vowel pronunciation metric for the second vowel sound; and

processing the first vowel pronunciation metric and the second vowel pronunciation metric to determine whether the non-native speech sample exhibits a distinction in pronunciation of the first vowel sound and the second vowel sound.

2. The method of claim 1, wherein the first vowel sound and the second vowel sound form a set of phonetically similar vowel sounds.

3. The method of claim 2, wherein a proficient native speaker pronounces the first vowel sound distinctly from the second vowel sound, and wherein a non-proficient non-native speaker pronounces the first vowel sound and the second vowel sound substantially identically.

4. The method of claim 2, wherein the set of phonetically similar vowel sounds includes one or more of:

/i/ versus /I/;

/e/ versus /ε

/;

/a/ versus //; and

/u/ versus //.

5. The method of claim 2, wherein the set of phonetically similar vowel sounds includes one or more of:

/i/ as in “

cheese”

versus /I/ as in “

six”

;

/e/ as in “

snake”

versus /ε

/ as in “

chess”

;

/a/ as in “

Bob”

versus // as in “

sun”

; and

/u/ as in “

food”

versus // as in “

good.”

6. The method of claim 1, wherein determining whether the non-native speech sample exhibits a distinction in pronunciation includes generating a vowel pronunciation score.

7. The method of claim 6, wherein a score based on the vowel pronunciation score is automatically provided via a graphical user interface to provide feedback on non-native speech proficiency.

8. The method of claim 7, wherein the feedback offers vowel pronunciation suggestions for improving communicative competence through better vowel pronunciation.

9. The method of claim 6, wherein the vowel pronunciation score is used to generate a speaking proficiency score for the speech sample.

10. The method of claim 1, wherein the vowel characteristics comprise vowel formant measurements.

11. The method of claim 10, wherein a vowel formant measurement comprises a measurement of an amplitude peak in a vowel spectrum that indicates a resonant frequency of a vowel.

12. The method of claim 1, wherein the first vowel pronunciation metric comprises an F2-F1 measurement, and wherein the second vowel pronunciation metric comprises an F2-F1 measurement.

13. The method of claim 12, wherein the distinction determination is based on a calculation of:

Dist(v_i, v_j)=√

{square root over ((F1_vi−

F1_vj)²+(F2_vi−

F2_vj)²)},

wherein F1_vi is a mean F1 measurement for vowel i, wherein F1_vj is a mean F1 measurement for vowel j, wherein F2_vi is a mean F2 measurement for vowel i, wherein F2_vj is a mean F2 measurement for vowel j.

14. The method of claim 1, further comprising performing automatic speech recognition on the non-native speech sample to generate a transcript, wherein the transcript is used to identify the vowel sound boundaries.

15. The method of claim 1, wherein a forced alignment procedure is used to identify the plurality of vowel sound boundaries.

16. The method of claim 1, wherein a non-native speech proficiency score is based on the distinction determination and further based on a stress metric, an intonation metric, a vocabulary metric, or a grammar metric.

17. A computer-implemented system for assessing non-native speech proficiency, comprising:

one or more data processors;

one or more computer-readable storage mediums encoded with instructions for commanding the one or more data processors to execute steps that include;

processing a non-native speech sample to identify a plurality of vowel sound boundaries in the non-native speech sample;

analyzing portions of the non-native speech sample within the vowel sound boundaries to extract vowel characteristics associated with a first vowel sound and a second vowel sound represented in the non-native speech sample;

processing the vowel characteristics to identify a first vowel pronunciation metric for the first vowel sound and a second vowel pronunciation metric for the second vowel sound; and

processing the first vowel pronunciation metric and the second vowel pronunciation metric to determine whether the non-native speech sample exhibits a distinction in pronunciation of the first vowel sound and the second vowel sound.

18. The system of claim 17, wherein the first vowel sound and the second vowel sound form a set of phonetically similar vowel sounds.

19. The system of claim 18, wherein a proficient native speaker pronounces the first vowel sound distinctly from the second vowel sound, and wherein a non-proficient non-native speaker pronounces the first vowel sound and the second vowel sound substantially identically.

20. The system of claim 17, wherein the set of phonetically similar vowel sounds includes one or more of:

/i/ versus /I/;

/e/ versus /ε

/;

/a/ versus //; and

/u/ versus //.

21. A non-transitory computer-readable storage medium comprising instructions for which when executed cause a processing system to execute steps comprising:

processing a non-native speech sample to identify a plurality of vowel sound boundaries in the non-native speech sample;

analyzing portions of the non-native speech sample within the vowel sound boundaries to extract vowel characteristics associated with a first vowel sound and a second vowel sound represented in the non-native speech sample;

processing the vowel characteristics to identify a first vowel pronunciation metric for the first vowel sound and a second vowel pronunciation metric for the second vowel sound; and

processing the first vowel pronunciation metric and the second vowel pronunciation metric to determine whether the non-native speech sample exhibits a distinction in pronunciation of the first vowel sound and the second vowel sound.