Terminal and method for voice control on terminal

• US 10,204,618 B2
• Filed: 11/09/2015
• Issued: 02/12/2019
• Est. Priority Date: 04/13/2015
• Status: Active Grant

• Current Assignee: Hisense International Company Limited (Qingdao Huatong State-Owned Capital Operation Company Limited), Hisense USA Corporation (Qingdao Huatong State-Owned Capital Operation Company Limited)
• Original Assignee: Hisense International Company Limited (Qingdao Huatong State-Owned Capital Operation Company Limited), Hisense Mobile Communications Technology Co., Ltd. (Qingdao Huatong State-Owned Capital Operation Company Limited), Hisense USA Corporation (Qingdao Huatong State-Owned Capital Operation Company Limited)
• Inventors: Dong, Tiantian, Du, Wenjuan, De, Gang
• Primary Examiner(s): Han, Qi
• Application Number:
  US14/935,701
• Publication Number:
  US 20160300567A1
• Time in Patent Office: 1,191 Days
• Field of Search: 704275, 704246, 704249, 704251, 704273
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

The application relates to a terminal and method for voice control on a terminal. A terminal according to some embodiments of the application includes: one or more processors, and a memory, wherein, the memory stores therein one or more computer readable program codes, and the processor or processors are configured to execute the one or more computer readable program codes, to match voice information in a voice instruction with preset voice information in the terminal upon reception of the voice instruction comprising the voice information and instruction information, to perform an operation corresponding to the instruction information upon determining successful matching, and to reject the operation corresponding to the instruction information upon determining unsuccessful matching.

Claims

1. A terminal comprising:

a processor; and

non-volatile memory storing therein one or more computer readable program codes, the processor configured to execute the one or more computer readable codes to;

during a first preset length of time, collect input speech via a microphone;

recognize one of multiple different speakers for each piece of different voice information in the collected input speech;

record in the memory, for each one of the multiple different speakers, an input duration during the first preset length of time of the piece of voice information corresponding to said one of the multiple different speakers; and

set the piece of voice information corresponding to the speaker having a longest input duration during the first preset length of time as preset voice information of an owner of the terminal for a subsequent voice matching process.

2. The terminal according to claim 1, further comprising an audio circuit, wherein after setting the piece of voice information corresponding to the speaker having the longest input duration during the first preset length of time as the preset voice information of the owner of the terminal for the subsequent voice matching process, the processor is further configured to execute the one or more computer readable codes to:

control the audio circuit to receive a voice instruction, the voice instruction comprising voice information and instruction information;

match the voice information in the voice instruction with the preset voice information in the terminal; and

in response to successful matching, perform an operation corresponding to the instruction information.

3. The terminal according to claim 2, wherein in response to successful matching, the processor is further configured to execute the one or more computer readable codes to:

determine and display a first virtual animation corresponding to the instruction information according to a correspondence relationship between the instruction information and the first virtual animation.

4. The terminal according to claim 2, wherein the processor is further configured to execute the one or more computer readable codes to:

determine the voice information in the voice instruction as other voice information than the preset voice information, and determine and display a second virtual animation corresponding to the other voice information according to a correspondence relationship between the other voice information and the second virtual animation.

5. The terminal according to claim 2, wherein the processor is further configured to execute the one or more computer readable codes to:

in response to determining unsuccessful matching, reject the operation corresponding to the instruction information.

6. The terminal according to claim 2, wherein the processor is further configured to execute the one or more computer readable codes to:

determine whether a condition to perform an operation of matching the voice information is satisfied, the condition to perform the operation of matching the voice operation including at least one of;

a current time is in a preset period of time for which the operation of matching the voice information needs to be performed, a current geographic position of the terminal is in a preset range in which the operation of matching the voice information needs to be performed, and an option displayed on the terminal is selected by a user to trigger the terminal to perform the operation of matching the voice operation.

7. The terminal according to claim 2, wherein, after setting the piece of voice information corresponding to the speaker having the longest input duration during the first preset length of time as the preset voice information of the owner of the terminal for the subsequent voice matching process, the processor is further configured to execute the one or more computer readable codes to:

during a second preset length of time, collect input speech via the microphone;

recognize voice information in the input speech collected during the second preset length of time;

set the recognized voice information in the input speech collected during the second preset length of time as revised voice information; and

match the voice information in the voice instruction with the preset voice information in the terminal by matching the voice information in the voice instruction with both the revised voice information and the preset voice information.

8. A method for voice control on a terminal, the method comprising:

during a first preset length of time, collecting input speech via a microphone;

recognizing one of multiple different speakers for each piece of different voice information in the collected input speech;

recording, for each one of the multiple different speakers, an input duration during the first preset length of time of the piece of voice information corresponding to said one of the multiple different speakers; and

setting the piece of voice information corresponding to the speaker having a longest input duration during the first preset length of time as preset voice information of an owner of the terminal for a subsequent voice matching process.

9. The method according to claim 8, wherein after setting the piece of voice information corresponding to the speaker having the longest input duration during the first preset length of time as the preset voice information of the owner of the terminal for the subsequent voice matching process, the method further comprises:

controlling an audio circuit of the terminal to receive a voice instruction, the voice instruction comprising voice information and instruction information;

matching the voice information in the voice instruction with the preset voice information in the terminal; and

when the matching is successful, performing an operation corresponding to the instruction information and displaying a visualization image corresponding to the operation on a display screen of the terminal.

10. The method according to claim 9, wherein the visualization image comprises a static image and a dynamic image.

11. The method according to claim 9, wherein the visualization image comprises a human image, an animal image, a plant image, a mechanical structure image, a cartoon image and/or an animated image.

12. The method according to claim 9, wherein the visualization image has an image expression corresponding to the operation.

13. The method according to claim 9, wherein before performing the operation corresponding to the instruction information, the method further comprises:

displaying a visualization image for welcome on the display screen.

14. The method according to claim 9, wherein the method further comprises:

in response to unsuccessful matching, displaying a visualization image for rejection on the display screen.

15. The method according to claim 8, after setting the piece of voice information corresponding to the speaker having the longest input duration during the first preset length of time as the preset voice information of the owner of the terminal for the subsequent voice matching process, the method further comprises:

controlling an audio circuit of the terminal to receive a voice instruction, the voice instruction comprising voice information and instruction information;

matching the voice information in the voice instruction with the preset voice information in the terminal; and

when the matching is successful, performing an operation corresponding to the instruction information.

16. The method according to claim 15, wherein when the matching is successful, the method further comprises:

determining and displaying a first virtual animation corresponding to the instruction information according to a correspondence relationship between the instruction information and the first virtual animation.

17. The method according to claim 15, wherein in response to unsuccessful matching, the method further comprises:

determining the voice information in the voice instruction as other voice information than the preset voice information; and

determining and displaying a second virtual animation corresponding to the other voice information according to a correspondence relationship between the other voice information and the second virtual animation.