Thought recollection and speech assistance device

• US 9,043,204 B2
• Filed: 09/12/2012
• Issued: 05/26/2015
• Est. Priority Date: 09/12/2012
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Berens, Scott H.
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/612,151
• Publication Number:
  US 20140074464A1
• Time in Patent Office: 986 Days
• Field of Search: 704/235, 704/243, 704/246, 704/248, 704/270, 704/271, 704/275, 704/251
• US Class Current: 704/235
• CPC Class Codes: G09B 21/009 Teaching or communicating with deaf persons G09B21/04 takes precedence; deaf and dumb persons G09B21/00
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

Some embodiments of the inventive subject matter include a method for detecting speech loss and supplying appropriate recollection data to the user. Such embodiments include detecting a speech stream from a user, converting the speech stream to text, storing the text, detecting an interruption to the speech stream, wherein the interruption to the speech stream indicates speech loss by the user, searching a catalog using the text as a search parameter to find relevant catalog data and, presenting the relevant catalog data to remind the user about the speech stream.

Claims

1. A method comprising:

detecting, via a microphone of an electronic device, an audible speech stream;

converting the audible speech stream to text;

detecting speech loss in the audible speech stream indicating an inability to complete a thought associated with the audible speech stream;

generating a query in response to the detecting the speech loss, wherein the query includes at least a portion of the text;

searching a catalog on the electronic device using the query to find related catalog data, wherein the catalog includes one or more of text strings, images, contact information, and global positioning system information associated with the electronic device; and

presenting the related catalog data.

2. The method of claim 1, wherein the related catalog data is presented visually.

3. The method of claim 1, wherein the related catalog data is presented audibly.

4. The method of claim 1, wherein the speech loss is detected by a divergence from a normal speech pattern.

5. The method of claim 1, wherein the speech loss is detected via user input.

6. The method of claim 1, wherein the detecting speech loss is trained via user training input.

7. The method of claim 1, wherein the speech loss is detected by a gap in speech which exceeds a predetermined length of time.

8. The method of claim 1, further comprising

distinguishing a user'"'"'s input from other speakers having conversations within the vicinity of the user, wherein the audible speech stream includes the user'"'"'s input.

9. The method of claim 1, wherein the related catalog data is presented via a preferred media-type, the preferred media-type indicated via user input.

10. An apparatus for speech-assist, the apparatus comprising:

a processor; and

a computer readable storage medium having computer usable program code embodied therewith, the computer usable program code executable by the processor to cause the apparatus to;

detect, via a microphone of the apparatus, an audible speech stream;

convert the audible speech stream to text;

detect speech loss in the audible speech stream indicating an inability to complete a thought associated with the audible speech stream;

generate a query in response to the detection of speech loss, wherein the query includes at least a portion of the text;

search a catalog on the apparatus using the query to find related catalog data, wherein the catalog includes one or more of text strings, images, contact information, and global positioning system information recently accessed via the apparatus; and

present, on at least one media presentation device of the apparatus, the related catalog data.

11. The apparatus of claim 10, wherein the apparatus is configured to detect the audible speech stream associated with a particular user.

12. The apparatus of claim 10, further comprising one or more input mechanisms operable to indicate the speech loss in the audible speech stream.

13. The apparatus of claim 10, further comprising one or more input mechanisms operable to train the apparatus to recognize the speech loss in the audible speech stream.

14. The apparatus of claim 10, further comprising a display device to present the search results.

15. The apparatus of claim 10, further comprising an audio output device to present the search results.

16. A non-transitory computer program product for speech-assist, the computer program product comprising:

a computer readable storage medium having computer usable program code embodied therewith, the computer usable program code comprising computer usable program code to;

detect, via a microphone, an audible speech stream;

convert the audible speech stream to text;

detect speech loss in the audible speech stream indicating an inability to complete a thought associated with the audible speech stream;

generate a query in response to the detection of speech loss, wherein the query includes at least a portion of the text;

search a local catalog using the query to find related catalog data, wherein the catalog includes one or more of text strings, images, contact information, and global positioning system information; and

present the related catalog data.

17. The non-transitory computer program product of claim 16, wherein the related catalog data is presented visually.

18. The non-transitory computer program product of claim 16, wherein the related catalog data is presented audibly.