Method and apparatus for reading education

• US 8,226,416 B2
• Filed: 12/07/2007
• Issued: 07/24/2012
• Est. Priority Date: 12/08/2006
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Abrash, Victor, Bercow, Douglas
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US11/952,713
• Publication Number:
  US 20080140401A1
• Time in Patent Office: 1,691 Days
• Field of Search: 704270-275, 434156-157, 434/178, 434/185
• US Class Current: 434/185
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G09B 5/04 with audible presentation of the material to be studied sound recording or reproducing G11B

Abstract

The present invention is a method and apparatus for reading education. In one embodiment, a method for recognizing an utterance spoken by a reader, includes receiving text to be read by the reader, generating a grammar for speech recognition, in accordance with the text, receiving the utterance, interpreting the utterance in accordance with the grammar, and outputting feedback indicative of reader performance.

Claims

1. A method for recognizing an utterance spoken by a reader, the method comprising:

receiving text comprising one or more words to be read by the reader;

generating a grammar for speech recognition, in accordance with the text;

inserting at least one reading learner grammar feature into the grammar, wherein the at least one reading learner grammar feature comprises a recognition of at least one reading learner mistake;

receiving the utterance;

interpreting the utterance in accordance with the grammar; and

outputting feedback indicative of reader performance.

2. Apparatus for recognizing an utterance spoken by a reader, the apparatus comprising:

means for receiving text comprising one or more words to be read by the reader;

means for generating a grammar for speech recognition, in accordance with the text;

means for inserting at least one reading learner grammar feature into the grammar, wherein the at least one reading learner grammar feature comprises a recognition of at least one reading learner mistake;

means for receiving the utterance; and

means for interpreting the utterance in accordance with the grammar; and

means for outputting feedback indicative of reader performance.

3. A non-transitory computer readable medium containing an executable program for recognizing an utterance spoken by a reader, where the program performs the steps of:

receiving text comprising one or more words to be read by the reader;

generating a grammar for speech recognition, in accordance with the text;

inserting at least one reading learner grammar feature into the grammar, wherein the at least one reading learner grammar feature comprises a recognition of at least one reading learner mistake;

receiving the utterance;

interpreting the utterance in accordance with the grammar; and

outputting feedback indicative of reader performance.

4. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises a structural restart.

5. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises a jump-ahead.

6. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises at least one pronunciation mistake.

7. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises a word insertion error or a word deletion error.

8. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises a mistake in directionality.

9. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words, skipping the next word.

10. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words, repeating a current word.

11. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words, uttering an immediately preceding word.

12. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words, uttering a beginning of a current phrase of which the current word is a part.

13. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words that is a line-ending word, repeating a current line.

14. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner mistake comprises, for at least one of the one or more words that is a line-ending word, uttering an immediately preceding line.

15. The non-transitory computer readable medium of claim 3, wherein the at least one reading learner grammar feature further comprises a reject grammar for at least one of the one or more words.

16. The non-transitory computer readable medium of claim 3, further comprising:

displaying the text to the reader prior to receiving the utterance.

17. The non-transitory computer readable medium of claim 16, wherein the displaying, the receiving of the utterance, and the interpreting are performed substantially simultaneously.

18. The non-transitory computer readable medium of claim 16, wherein the displaying comprises:

formatting the text for display.

19. The non-transitory computer readable medium of claim 18, wherein the text further comprises a formatting markup for guiding the formatting.

20. The non-transitory computer readable medium of claim 19, wherein the formatting comprises:

calculating a position of at least one text format feature in accordance with at least one characteristic of a device on which the text is to be displayed.

21. The non-transitory computer readable medium of claim 3, wherein the text further comprises metadata comprising semantic data.

22. The non-transitory computer readable medium of claim 3, wherein the feedback comprises at least partial results of the interpreting.

23. The non-transitory computer readable medium of claim 3, wherein the feedback comprises a score indicative of an accuracy of the utterance relative to the text.

24. The non-transitory computer readable medium of claim 23, wherein the score comprises at least one of:

a number of words uttered by the reader in a given period of time, an amount of time taken by the reader to complete utterance of at least a portion of the text, a confidence score relating to a word uttered by the reader, a confidence score relating to a sentence uttered by the reader, a confidence score relating to a phrase uttered by the reader, or a percentage of words correctly uttered by the reader.

25. The non-transitory computer readable medium of claim 23, wherein the score is at least one of:

a dialog act score, a duration score, a fluency score, a score related to a path taken through the grammar, or a pronunciation score.

26. The non-transitory computer readable medium of claim 3, wherein the feedback comprises at least one of:

poorly uttered portions of the text, correctly uttered portions of the text, skipped portion of the text, or repeated portions of the text.

27. The non-transitory computer readable medium of claim 3, further comprising:

storing the feedback.

28. The non-transitory computer readable medium of claim 3, wherein the inserting comprises:

generating transitions representing a correct utterance of the text; and

generating transitions representing the at least one reading learner grammar feature.

29. The non-transitory computer readable medium of claim 28, wherein the transitions representing the correct utterance and the transitions representing the at least one reading learner feature are assigned probabilities.

30. The non-transitory computer readable medium of claim 28, wherein at least one word in at least one of the correct utterance and the transitions representing the at least one reading learner grammar feature is represented by a multi-word sub-grammar, the multi-word sub-grammar comprising:

the at least one word;

a reject grammar; and

a pause grammar.

31. The non-transitory computer readable medium of claim 3, wherein the text is received from local storage.

32. The non-transitory computer readable medium of claim 3, wherein the text is received from a remote computing device.

33. The non-transitory computer readable medium of claim 3, wherein the receiving text comprises:

performing optical character recognition on a piece of printed text.