Biasing voice correction suggestions

• US 10,679,609 B2
• Filed: 12/03/2019
• Issued: 06/09/2020
• Est. Priority Date: 01/05/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Cherepanov, Evgeny A., Foerster, Jakob Nicolaus, Sridar, Vikram, Rabinovitz, Ishai, Tabach, Omer
• Primary Examiner(s): Patel, Shreyans A
• Application Number:
  US16/701,685
• Publication Number:
  US 20200105247A1
• Time in Patent Office: 189 Days
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.

Claims

1. A method comprising:

receiving, at a user device, a voice input from a user of the user device;

displaying, by the user device, an initial recognition output in a graphical user interface based on the voice input, the initial recognition output comprising an initial transcription of the voice input, the initial transcription comprising a misrecognized term;

receiving, at the user device, a selection indication indicating a user selection in the graphical user interface of a portion of the initial recognition output to correct the misrecognized term;

after receiving the selection indication, displaying, by the user device, a first list of suggested recognition outputs of the voice input in the graphical user interface, each suggested recognition output of the first list comprising a respective phonetic similarity to the received voice input;

after displaying the first list of suggested recognition outputs, receiving, at the user device, one or more text characters inputted by the user through the graphical user interface; and

replacing, by the user device, the misrecognized term based on the received one or more text characters to provide a corrected transcription of the voice input.

2. The method of claim 1, wherein replacing the misrecognized term based on the received one or more text characters comprises:

displaying, in the graphical user interface, a second list of suggested recognition outputs in response to receiving the one or more text characters inputted by the user, each suggested recognition output of the second list of suggested recognition outputs comprising a respective phonetic similarity to the one or more text characters;

receiving another selection indication indicating a user selection in the graphical user interface of one of the suggested recognition outputs of the second list of suggested recognition outputs; and

replacing the misrecognized term using the selected suggested recognition output of the second list of suggested recognition outputs.

3. The method of claim 2, further comprising iteratively identifying, by the user device, the suggested recognition outputs for inclusion in the second list of suggested recognition outputs displayed in the graphical user interface responsive to receiving each text character of the one or more text characters.

4. The method of claim 1, further comprising displaying, by the user device, in the graphical user interface, the one or more text characters inputted by the user through the graphical user interface.

5. The method of claim 1, wherein the one or more text characters comprise one or more letters inputted by the user through the graphical user interface.

6. The method of claim 1, further comprising, in response to receiving the selection indication, displaying, by the user device, a keyboard in the graphical user interface.

7. The method of claim 1, wherein the first list of suggested recognition outputs of the voice input displayed in the graphical user interface are ranked according to the respective phonetic similarity between each suggested recognition output and the received voice input.

8. The method of claim 1, wherein the first list of suggested recognition outputs of the voice input displayed in the graphical user interface are based on a popularity of the suggested recognition outputs.

9. The method of claim 1, further comprising, after receiving the selection indication, superimposing, by the user device, a graphical indicator in the graphical user interface over the misrecognized term of the initial transcription.

10. The method of claim 1, wherein the initial recognition output corresponds to an action of inputting text in a text editor or an electronic message.

11. A user device comprising:

data processing hardware; and

memory hardware in communication with the data processing hardware and storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising;

receiving a voice input from a user of the user device;

displaying an initial recognition output in a graphical user interface based on the voice input, the initial recognition output comprising an initial transcription of the voice input, the initial transcription comprising a misrecognized term;

receiving a selection indication indicating a user selection in the graphical user interface of a portion of the initial recognition output to correct the misrecognized term;

after receiving the selection indication, displaying a first list of suggested recognition outputs of the voice input in the graphical user interface, each suggested recognition output of the first list comprising a respective phonetic similarity to the received voice input;

after displaying the first list of suggested recognition outputs, receiving one or more text characters inputted by the user through the graphical user interface; and

replacing the misrecognized term based on the received one or more text characters to provide a corrected transcription of the voice input.

12. The user device of claim 11, wherein replacing the misrecognized term based on the received one or more text characters comprises:

displaying, in the graphical user interface, a second list of suggested recognition outputs in response to receiving the one or more text characters inputted by the user, each suggested recognition output of the second list of suggested recognition outputs comprising a respective phonetic similarity to the one or more text characters;

receiving another selection indication indicating a user selection in the graphical user interface of one of the suggested recognition outputs of the second list of suggested recognition outputs; and

replacing the misrecognized term using the selected suggested recognition output of the second list of suggested recognition outputs.

13. The user device of claim 12, wherein the operations further comprise iteratively identifying the suggested recognition outputs for inclusion in the second list of suggested recognition outputs displayed in the graphical user interface responsive to receiving each text character of the one or more text characters.

14. The user device of claim 11, wherein the operations further comprise, displaying in the graphical user interface, the one or more text characters inputted by the user through the graphical user interface.

15. The user device of claim 11, wherein the one or more text characters comprise one or more letters inputted by the user through the graphical user interface.

16. The user device of claim 11, wherein the operations further comprise, in response to receiving the selection indication, displaying a keyboard in the graphical user interface.

17. The user device of claim 11, wherein the first list of suggested recognition outputs of the voice input displayed in the graphical user interface are ranked according to the respective phonetic similarity between each suggested recognition output and the received voice input.

18. The user device of claim 11, wherein the first list of suggested recognition outputs of the voice input displayed in the graphical user interface are based on a popularity of the suggested recognition outputs.

19. The user device of claim 11, wherein the operations further comprise, after receiving the selection indication, superimposing a graphical indicator in the graphical user interface over the misrecognized term of the initial transcription.

20. The user device of claim 11, wherein the initial recognition output corresponds to an action of inputting text in a text editor or an electronic message.