Method, apparatus, and computing device for revision of speech recognition results

• US 10,796,699 B2
• Filed: 12/07/2017
• Issued: 10/06/2020
• Est. Priority Date: 12/08/2016
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Guangzhou SHENMA Information Technology Co. Ltd.
• Inventors: Yu, Zhichao, Zheng, Zhihui
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US15/835,248
• Publication Number:
  US 20180166080A1
• Time in Patent Office: 1,034 Days
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G10L 15/063 Training
• 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 2015/0638 Interactive procedures
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

The present disclosure discloses an information input method and device, and a computing apparatus. The information input method comprises receiving a voice input of a user, acquiring a recognition result on the received voice input, and enabling editing of the acquired recognition result in a text format. With the information input mechanism, according to the present invention, a user is able to choose to revise an automatic speech recognition result in a text editing format, particularly in the case where a small amount of errors occurs to the contents of speech recognition. As a result, the trouble that all contents of a voice input need to be input again is avoided, the speech recognition efficiency is increased, and the user experience is improved.

Claims

1. An information input method, comprising:

receiving a voice input of a user;

sending the received voice input to a server;

displaying an animation having a continuous refresh rate while the server determines, based on a speech recognition model, recognition results on the received voice input;

acquiring, from the server, a list of the recognition results;

in response to the list of the recognition results being acquired, hiding the animation and replacing the animation with a display of the list of the recognition results;

providing an interface to revise a recognition result in the list of the acquired recognition results, the providing the interface comprising;

in response to the user single clicking, double clicking, or hovering over an editing mode logo for the recognition result, sliding, for a duration distinct from the continuous refresh rate of the animation, the interface from a bottom of a screen of a display device in an accelerating and subsequently decelerating manner; and

in response to revising the recognition result, feeding the revised recognition result to the server to train the speech recognition model.

2. The information input method according to claim 1, wherein the providing the interface to revise the recognition result further comprises:

entering, in response to the interface being slid from the bottom of the screen of the display device, a text editing mode.

3. The information input method according to claim 2, wherein the providing the interface to revise the recognition result further comprises:

presenting, in an associated manner, an editing mode logo for the recognition result; and

entering, in response to a trigger of the editing mode logo by the user, the text editing mode.

4. The information input method according to claim 1, further comprising:

determining a recognition result selected by the user from the list of the recognition results as an acquired recognition result,

wherein the providing the interface to revise the acquired recognition result further comprises;

enabling the user to edit any recognition result in the list of recognition results in a text format in response to the user not selecting any recognition result in the list of recognition results.

5. The information input method according to claim 1, further comprising, in response to providing the interface to revise the recognition result, accepting a revision by the user without prompting the user for another voice input.

6. The information input method according to claim 3, wherein, the presenting an editing mode logo for the recognition result comprises presenting the editing mode logo in response to a posture action by the user.

7. The information input method according to claim 1, further comprising:

in response to revising the recognition result;

initiating, by the remote server, a search using the revised recognition result;

creating a window to present results of the search.

8. The information input method according to claim 1, wherein the animation comprises a microphone logo implemented by a function comprising a plot of three parameterized lines.

9. An information input device, comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the device to perform;

receiving a voice input of a user;

sending the received voice input to a server;

displaying an animation having a continuous refresh rate while a server determines, based on a speech recognition model, recognition results on the received voice input;

acquiring, from the server, a list of the recognition results;

in response to the list of the recognition results being acquired, hiding the animation and replacing the animation with a display of the list of the recognition results;

providing an interface to revise a recognition result in the list of the acquired recognition results, the providing the interface comprising;

in response to the user single clicking, double clicking, or hovering over an editing mode logo for the recognition result, sliding, for a duration distinct from the continuous refresh rate of the animation, the interface from a bottom of a screen of a display device, in an accelerating and subsequently decelerating manner; and

in response to revising the recognition result, feeding the revised recognition result to the server to train the speech recognition model.

10. The information input device according to claim 9, wherein the providing the interface to revise the recognition result further comprises:

entering, in response to the interface being slid from the bottom of the screen of the display device, a text editing mode.

11. The information input device according to claim 10, wherein the providing the interface to revise the recognition result further comprises:

presenting, in an associated manner, an editing mode logo for the recognition result; and

entering, in response to a trigger of the editing mode logo by the user, the text editing mode.

12. The information input device according to claim 9, wherein the instructions further cause the device to perform:

determining a recognition result selected by the user from the list of the recognition results as an acquired recognition result,

and wherein the providing the interface to revise the recognition result further comprises;

enabling the user to edit any recognition result in the list of recognition results in a text format in response to the user not selecting any recognition result in the list of recognition results.

13. A computing apparatus, comprising:

a network interface, configured to enable the computing apparatus to conduct data communications with a server via one or more networks;

a memory configured to store data communicated via the network interface; and

one or more processors in connection with the network interface and the memory, the one or more processors being configured to execute the following operations;

receiving a voice input of a user;

sending the received voice input to a server;

displaying an animation having a continuous refresh rate while a server determines, based on a speech recognition model, recognition results on the received voice input;

acquiring, from the server, a list of the recognition results;

in response to the list of the recognition results being acquired, hiding the animation and replacing the animation with a display of the list of the recognition results;

providing an interface to revise a recognition result in the list of the recognition results, the providing the interface comprising;

in response to the user single clicking, double clicking, or hovering over an editing mode logo for the recognition result, sliding, for a duration distinct from the continuous refresh rate of the animation, the interface from a bottom of a screen of a display device in an accelerating and subsequently decelerating manner; and

in response to revising the recognition result, feeding the revised recognition result to the server to train the speech recognition model.

14. The computing apparatus according to claim 13, wherein the operation of providing the interface to revise the recognition result further comprises:

entering, in response to the interface being slid from the bottom of the screen of the display device, a text editing mode.

15. The computing apparatus according to claim 14, wherein the providing the interface to revise the recognition result further comprises:

presenting, in an associated manner, an editing mode logo for the recognition result; and

entering, in response to a trigger of the editing mode logo by the user, the text editing mode to revise the recognition result.

16. The computing apparatus according to claim 13, wherein the operations further comprise:

determining a recognition result selected by the user from the list of the recognition results as an recognition result,

wherein the providing the interface to revise the recognition result comprises;

enabling the user to edit any recognition result in the list of recognition results in a text format in response to the user not selecting any recognition result in the list of recognition results.