Biasing voice correction suggestions

• US 10,242,662 B1
• Filed: 10/20/2017
• Issued: 03/26/2019
• Est. Priority Date: 01/05/2016
• Status: Active Grant

• Current Assignee: Google Inc. (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:
  US15/789,575
• Time in Patent Office: 522 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, the voice input comprising a search query;

displaying, by the user device, an initial transcription of the search query in a graphical user interface, the initial transcription including a misrecognized term;

receiving, at the user device, a selection indication indicating a user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query;

after receiving the selection indication, receiving, at the user device, a prefix inputted by the user through the graphical user interface, the prefix replacing the misrecognized term of the initial transcription of the search query; and

displaying, by the user device, a list of candidate transcriptions for the search query in the graphical user interface, the list of candidate transcription ranked according to a respective phonetic similarity between each candidate transcription and the received voice input, each candidate transcription comprising the prefix and having a respective score that satisfies a threshold score value.

2. The method of claim 1, further comprising:

receiving, at the user device, a text character inputted by the user through the graphical user interface that follows the prefix; and

displaying, by the user device, an updated list of candidate transcriptions of the search query in the graphical user interface, the updated list of candidate transcriptions ranked according to a respective phonetic similarity between each candidate transcription in the updated list and the received voice input, each candidate transcription in the updated list comprising the prefix and the text character.

3. The method of claim 2, wherein the text character includes a letter.

4. The method of claim 1, further comprising:

receiving, at the user device, another selection indication indicating another user selection in the graphical user interface of one of the candidate transcriptions displayed in the graphical user interface as a corrected transcription of the search query; and

displaying, by the user device, one or more search results corresponding to the corrected transcription of the search query in the graphical user interface.

5. The method of claim 4, further comprising, when displaying the one or more search results corresponding to the corrected transcription of the search query, displaying, by the user device, the corrected transcription of the search query in the graphical user interface of the user device.

6. The method of claim 1, further comprising:

prior to receiving the selection indication indicating the user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query, displaying, by the user device, one or more initial search results corresponding to the initial transcription of the search query;

after displaying the list of candidate transcriptions for the search query, receiving, at the user device, another selection indication indicating another user selection in the graphical user interface of one of the displayed candidate transcriptions as a corrected transcription of the search query; and

updating, by the user device, the one or more initial search results corresponding to the initial transcription of the search query displayed in the graphical user interface with one or more corrected search results corresponding to the corrected transcription of the search query.

7. The method of claim 1, further comprising, in response to receiving the selection indication of the user selection in the graphical user interface of the misrecognized term, superimposing, by the user device, a graphical indicator in the graphical user interface that indicates the selection of the misrecognized term of the initial transcription of the search query.

8. A system comprising:

one or more computers of a user device and one or more storage devices of the user device storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving a voice input from a user of the user device, the voice input comprising a search query;

displaying an initial transcription of the search query in a graphical user interface, the initial transcription including a misrecognized term;

receiving a selection indication indicating a user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query;

after receiving the selection indication, receiving a prefix inputted by the user through the graphical user interface, the prefix replacing the misrecognized term of the initial transcription of the search query; and

displaying a list of candidate transcriptions for the search query in the graphical user interface, the list of candidate transcriptions ranked according to a respective phonetic similarity between each candidate transcription and the received voice input, each candidate transcription comprising the prefix and having a respective score that satisfies a threshold score value.

9. The system of claim 8, wherein the operations further comprise:

receiving a text character inputted by the user through the graphical user interface that follows the prefix; and

displaying an updated list of candidate transcriptions of the search query in the graphical user interface, the updated list of candidate transcriptions ranked according to a respective phonetic similarity between each candidate transcription in the updated list and the received voice input, each candidate transcription in the updated list comprising the prefix and the text character.

10. The system of claim 9, wherein the text character includes a letter.

11. The system of claim 8, wherein the operations further comprise:

receiving another selection indication indicating another user selection in the graphical user interface of the candidate transcriptions displayed in the graphical user interface as a corrected transcription of the search query; and

displaying one or more search results corresponding to the corrected transcription of the search query in the graphical user interface.

12. The system of claim 11, wherein the operations further comprise, when displaying the one or more search results corresponding to the corrected transcription of the search query, displaying the corrected transcription of the search query in the graphical user interface of the user device.

13. The system of claim 8, wherein the the operations further comprise:

prior to receiving the selection indication indicating the user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query, displaying one or more initial search results corresponding to the initial transcription of the search query;

after displaying the list of candidate transcriptions for the corrected transcription of the search query, receiving another selection indication indicating another user selection in the graphical user interface of one of the displayed candidate transcriptions as a corrected transcription of the search query; and

updating the one or more initial search results corresponding to the initial transcription of the search query displayed in the graphical user interface with one or more corrected search results corresponding to the corrected transcription of the search query.

14. The system of claim 8, wherein the operations further comprise, in response to receiving the selection indication indicating the user selection in the graphical user interface of the misrecognized term, superimposing, by the user device, a graphical indicator in the graphical user interface that indicates the selection of the misrecognized term of the initial transcription of the search query.

15. One or more non-transitory computer-readable storage medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

receiving a voice input from a user of the user device, the voice input comprising a search query;

displaying an initial transcription of the search query in a graphical user interface, the initial transcription including a misrecognized term;

receiving a selection indication indicating a user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query;

after receiving the selection indication, receiving a prefix inputted by the user through the graphical user interface, the prefix replacing the misrecognized term of the initial transcription of the search query; and

displaying a list of candidate transcriptions for the search query in the graphical user interface, the list of candidate transcriptions ranked according to a respective phonetic similarity between each candidate transcription and the received voice input, each candidate transcription comprising the prefix and having a respective score that satisfies a threshold score value.

16. The non-transitory computer-readable storage medium of claim 15, wherein the operations further comprise:

receiving a text character inputted by the user through the graphical user interface that follows the prefix; and

displaying an updated list of candidate transcriptions of the search query in the graphical user interface, the updated list of candidate transcriptions ranked according to a respective phonetic similarity between each candidate transcription in the updated list and the received voice input, each candidate transcription in the updated list comprising the prefix and the text character.

17. The non-transitory computer-readable storage medium of claim 15, wherein the operations further comprise:

receiving another selection indication indicating another user selection in the graphical user interface of the candidate transcriptions displayed in the graphical user interface as a corrected transcription of the search query; and

displaying one or more search results corresponding to the corrected transcription of the search query in the graphical user interface.

18. The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise, when displaying the one or more search results corresponding to the corrected transcription of the search query, displaying the corrected transcription of the search query in the graphical user interface of the user device.

19. The non-transitory computer-readable storage medium of claim 15, wherein the the operations further comprise:

prior to receiving the selection indication indicating the user selection in the graphical user interface of the misrecognized term of the initial transcription of the search query, displaying one or more initial search results corresponding to the initial transcription of the search query;

after displaying the list of candidate transcriptions for the corrected transcription of the search query, receiving another selection indication indicating another user selection in the graphical user interface of one of the displayed candidate transcriptions as a corrected transcription of the search query; and

updating the one or more initial search results corresponding to the initial transcription of the search query displayed in the graphical user interface with one or more corrected search results corresponding to the corrected transcription of the search query.

20. The non-transitory computer-readable storage medium of claim 15, wherein the operations further comprise, in response to receiving the selection indication indicating the user selection in the graphical user interface of the misrecognized term, superimposing, by the user device, a graphical indicator in the graphical user interface that indicates the selection of the misrecognized term of the initial transcription of the search query.