Audio reader

• US 6,195,640 B1
• Filed: 01/29/1999
• Issued: 02/27/2001
• Est. Priority Date: 01/29/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Mullaly, John Martin, Burleson, Winslow Scott
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US09/240,500
• Time in Patent Office: 760 Days
• Field of Search: 704/256, 704/257, 704/258, 704/260, 345/156, 345/157
• US Class Current: 704/260
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

The present invention provides a method for allowing a user'"'"'s reading to dictate the speed and position at which content is converted to audio in an audio reader. The method includes determining a position of a user'"'"'s eye gaze, identifying a content displayed at the position of the user'"'"'s eye gaze, determining an audio corresponding to the content, and outputting the audio. The method of the present invention allows the user'"'"'s reading to drive the text to speech conversion, resulting in the computer reading what the user is currently reading. The user may then read text at a variable rate and at different positions, with the text to speech conversion following the user. The method of the present invention may be used to help raise users'"'"' literacy levels, to help users learn to read faster, to help boost reading comprehension, to help users scan documents, and to provide feedback for positioning and control. The present invention is thus flexible and has a range of utilities.

Claims

1. A method for allowing a user'"'"'s reading speed to dictate the speed at which content is converted to audio in an audio reader, comprising the steps of:

(a) determining a position of a user'"'"'s eye gaze;

(b) identifying a text displayed at the position of the user'"'"'s eye gaze;

(c) converting the text to audio at a speed based upon the user'"'"'s reading speed; and

(d) outputting the audio.

2. The method of claim 1, wherein the audio comprises speech.

3. The method of claim 1, wherein the determining step (a) comprises:

(a1) tracking the position of the user'"'"'s eye gaze utilizing an eye-tracking subsystem.

4. The method of claim 1, wherein the converting step (c) comprises:

(c1) converting the text to audio utilizing a text to speech subsystem.

5. The method of claim 1, wherein the converting step (c) comprises:

(c1) identifying a prerecorded audio file corresponding to the text utilizing a text to speech subsystem.

6. The method of claim 1, further comprising:

(e) detecting a first change in the position of the user'"'"'s eye gaze;

(f) determining if the first change is directed motion; and

(g) repeating steps (a) through (d) if the first change is directed motion.

7. The method of claim 6, further comprising:

(h) waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

8. An audio reader, comprising:

a display device displaying a plurality of texts;

an audio output device; and

a computer coupled to the display device and the audio output device, wherein the computer comprises

means for determining a position of a user'"'"'s eye gaze,

means for identifying a text of the plurality of texts displayed on the display device at the position of the user'"'"'s eye gaze, and

means for converting the text to audio at a speed based upon a user'"'"'s reading speed, wherein the audio is outputted utilizing the audio output device.

9. The audio reader of claim 8, wherein the audio comprises speech.

10. The audio reader of claim 8, wherein the means for determining a position of a user'"'"'s eye gaze comprises:

means for tracking the position of the user'"'"'s eye gaze utilizing an eye-tracking subsystem.

11. The audio reader of claim 8, wherein the converting means comprises:

means for converting the text to audio utilizing a text to speech subsystem.

12. The audio reader of claim 8, wherein the converting means comprises:

means for identifying a prerecorded audio file corresponding to the content utilizing a text to speech subsystem.

13. The audio reader of claim 8, wherein the computer further comprises:

means for detecting a first change in the position of the user'"'"'s eye gaze; and

means for determining if the first change is directed motion, wherein the determining means, identifying means, and converting means are utilized if the first change is directed motion.

14. The audio reader of claim 13, further comprising:

means for waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

15. A method for allowing a user'"'"'s reading speed to dictate the speed at which content is converted to audio in an audio reader, comprising the steps of:

(a) tracking a position of a user'"'"'s eye gaze utilizing an eye-tracking subsystem;

(b) identifying a text displayed at the position of the user'"'"'s eye gaze;

(c) converting the text to audio at a speed based upon the user'"'"'s reading speed utilizing a text to speech subsystem; and

(d) outputting the audio.

16. The method of claim 15, wherein the audio comprises speech.

17. The method of claim 15, further comprising:

(e) detecting a first change in the position of the user'"'"'s eye gaze;

(f) determining if the first change is directed motion; and

(g) repeating steps (a) through (d) if the first change is directed motion.

18. The method of claim 17, further comprising:

(h) waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

19. An audio reader, comprising:

a display device displaying a plurality of texts;

an audio output device; and

a computer coupled to the display device and the audio output device, wherein the computer comprises

an eye-tracking subsystem for tracking a position of the user'"'"'s eye gaze,

an interface and converting subsystem for identifying a text of the plurality of texts displayed on the display device at the position of the user'"'"'s eye gaze, and

a text to speech subsystem for converting the text to audio at a speed based upon a user'"'"'s reading speed, wherein the audio is outputted utilizing the audio output device.

20. The audio reader of claim 19, wherein the audio comprises speech.

21. The audio reader of claim 19, wherein the computer further comprises:

means for detecting a first change in the position of the user'"'"'s eye gaze;

means for determining if the first change is directed motion, wherein the determining means, identifying means, and converting means are utilized if the first change is directed motion.

22. The audio reader of claim 21, further comprising:

means for waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

23. A method for allowing a user'"'"'s reading speed to dictate the speed at which content is converted to audio in an audio reader, comprising the steps of:

(a) tracking a position of a user'"'"'s eye gaze utilizing an eye-tracking subsystem;

(b) identifying a text displayed at the position of the user'"'"'s eye gaze;

(c) converting the text to audio at a speed based upon the user'"'"'s reading speed utilizing a text to speech subsystem;

(d) outputting the audio;

(e) detecting a first change in the position of the user'"'"'s eye gaze;

(f) determining if the first change is directed motion; and

(g) repeating steps (a) through (d) if the first change is directed motion.

24. The method of claim 23, further comprising:

(h) waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

25. An audio reader, comprising:

a display device displaying a plurality of texts;

an audio output device; and

a computer coupled to the display device and the audio output device, wherein the computer comprises

an eye-tracking subsystem for tracking a position of the user'"'"'s eye gaze,

an interface and converting subsystem for identifying a text of the plurality of texts displayed on the display device at the position of the user'"'"'s eye gaze,

a text to speech subsystem for converting the text to audio at a speed based upon the user'"'"'s reading speed, wherein the audio is outputted utilizing the audio output device,

means for detecting a first change in the position of the user'"'"'s eye gaze, and

means for determining if the first change is directed motion, wherein the eye-tracking subsystem and the text to speech subsystem, and the interface and converting subsystem are utilized if the first change is directed motion.

26. The audio reader of claim 25, further comprising:

means for waiting for a second change in the position of the user'"'"'s eye gaze if the first change is not a directed motion.

27. A computer readable medium with computer instructions for allowing a user'"'"'s reading speed to dictate the speed at which content is converted to audio in an audio reader, the computer instructions for:

(a) determining a position of a user'"'"'s eye gaze;

(b) identifying a text displayed at the position of the user'"'"'s eye gaze;

(c) converting the text to audio at a speed based upon the user'"'"'s reading speed; and

(d) outputting the audio.