Interactive text editing

• US 8,290,772 B1
• Filed: 10/11/2011
• Issued: 10/16/2012
• Est. Priority Date: 10/03/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zanolin, Luca, Cohen, Richard Z., Foster, Marcus A.
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US13/270,927
• Time in Patent Office: 371 Days
• Field of Search: 704/235, 704/251, 715/257, 369/25.01
• US Class Current: 704/235
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

A method for providing suggestions includes capturing audio that includes speech and receiving textual content from a speech recognition engine. The speech recognition engine performs speech recognition on the audio signal to obtain the textual content, which includes one or more passages. The method also includes receiving a selection of a portion of a first word in a passage in the textual content, wherein the passage includes multiple words, and retrieving a set of suggestions that can potentially replace the first word. At least one suggestion from the set of suggestions provides a multi-word suggestion for potentially replacing the first word. The method further includes displaying, on a display device, the set of suggestions, and highlighting a portion of the textual content, as displayed on the display device, for potentially changing to one of the suggestions from the set of suggestions.

Claims

1. A method for providing suggestions, the method comprising:

capturing audio that includes speech;

receiving textual content from a speech recognition engine, wherein;

the speech recognition engine performs speech recognition on the audio to obtain the textual content, and

the textual content includes one or more passages;

receiving a selection of a portion of a first word in a passage in the textual content, wherein the passage includes multiple words;

retrieving a set of presentable suggestions that can potentially replace the first word, wherein at least one suggestion from the set of suggestions provides a multi-word suggestion for potentially replacing the first word, wherein retrieving the set of presentable suggestions includes selecting a second set of suggestions from a first set of suggestions that can potentially change the passage;

displaying, on a display device, the second set of suggestions; and

highlighting a portion of the textual content, as displayed on the display device, for potentially changing to one of the suggestions from the second set of suggestions.

2. The method of claim 1, wherein the first set of suggestions includes words and phrases that can potentially change one or more portions of the passage, the one or more portions including the first word.

3. The method of claim 1, wherein the highlighting is based on the second set of suggestions.

4. The method of claim 3, further comprising determining a global correction span corresponding to the second set of suggestions, the global correction span including all the words from the passage that could potentially be changed by the second set of suggestions.

5. The method of claim 4, wherein the global correction span is determined as a union of the corrections spans corresponding to the individual suggestions in the second set of suggestions.

6. The method of claim 1, wherein the second set of suggestions comprises a predetermined number of suggestions from the first set of suggestions.

7. The method of claim 6, wherein the predetermined number depends on an available area on the user interface.

8. The method of claim 6, wherein the predetermined number of suggestions is selected from the first set based on an order of appearance of the suggestions in a ranked list derived from the first set.

9. The method of claim 1, wherein displaying the set of suggestions further comprises:

adding one or more words from the passage to one or more of the suggestions from the second set; and

visually distinguishing the added words from other words in the suggestions.

10. A system comprising:

a suggestion engine configured to;

retrieve, in response to a selection of a portion of a first word in a passage, a first set of suggestions to change the first word, and

select from the first set, a second set of suggestions, wherein at least one suggestion from the second set of suggestions provides a multi-word suggestion for potentially replacing the first word; and

a user interface rendered on a display device, the user interface configured to;

display the second set of suggestions, and

display a highlighted portion of the passage for potentially changing to one of the second set of suggestions.

11. The system of claim 10, further comprising a suggestion repository configured to store suggestions related to the passage and provide one or more of the stored suggestions to the suggestion engine as the first set of suggestions.

12. The system of claim 10, wherein the suggestion engine is further configured to determine a range of the highlighted portion of the passage based on the second set of suggestions.

13. The system of claim 10, wherein the suggestion engine is further configured to determine a global correction span corresponding to the second set of suggestions, the global correction span including all the words from the passage that could potentially be changed by the second set of suggestions.

14. The system of claim 13, wherein the global correction span is determined as a union of the corrections spans corresponding to the individual suggestions in the second set of suggestions.

15. The system of claim 11, wherein the suggestion repository resides on a computing device on which the suggestion engine is implemented.

16. The system of claim 15, wherein the display device is a part of the computing device.

17. The system of claim 15, wherein the computing device is a smartphone.

18. The system of claim 10, wherein the user interface is configured to display a predetermined number of suggestions and the suggestion engine is further configured to limit a size of the second set of suggestions to the predetermined number.

19. The system of claim 18, wherein the suggestion engine is further configured to select the predetermined number of suggestions for the second set based on an order of appearance of the suggestions in a ranked list derived from the first set.

20. The system of claim 10, wherein the suggestion engine is further configured to add one or more words from the passage to one or more of the suggestions in the second set.

21. The system of claim 20, wherein the user interface is further configured to display the second set such that the added words are visually distinguished from other words in the suggestions.

22. The system of claim 10, wherein the passage is provided from textual content received from a speech recognition engine.

23. A computer program product comprising computer readable instructions tangibly embodied in a storage device, the instructions configured to cause one or more processors to:

receive a selection of a portion of a first word in a passage;

retrieve a first set of suggestions to change the first word;

select, from the first set, a second set of suggestions, wherein at least one suggestion from the second set provides a multi-word suggestion for the first word;

display, using an user interface, the second set of suggestions; and

highlight a portion of the passage, as displayed on a display device, for potentially changing to one of the second set of suggestions.

24. The computer program product of claim 23, wherein the instructions are further configured to cause one or more processors to determine a global correction span corresponding to the second set of suggestions, the global correction span including all the words from the passage that could potentially be changed by the second set of suggestions.

25. The computer program product of claim 24, wherein the portion of the passage that is highlighted substantially corresponds to the global correction span.

26. The computer program product of claim 23, wherein the instructions are further configured to cause one or more processors to:

add one or more words from the passage to one or more of the suggestions from the second set; and

visually distinguish the added words from other words in the suggestions.