Virtual reality speech control method and apparatus

• US 10,714,090 B2
• Filed: 10/13/2017
• Issued: 07/14/2020
• Est. Priority Date: 10/14/2016
• Status: Active Grant

• Current Assignee: Beijing Baidu Netcom Science and Technology Company Limited (Baidu Incorporated)
• Original Assignee: Beijing Baidu Netcom Science and Technology Company Limited (Baidu Incorporated)
• Inventors: Liu, Xiaoqian
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US15/783,344
• Publication Number:
  US 20180108357A1
• Time in Patent Office: 1,005 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• 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 2015/223 Execution procedure of a spoken command

Abstract

A virtual reality speech control method and apparatus is provided in the present disclosure. The method includes: receiving a request for opening a speech interface from a VR application; opening a speech interface in response to the request and receiving input speech information through the speech interface; converting the speech information to text information, and normalizing the text information to generate an intent object in conformity with a preset specification; recognizing the intent object based on a preset specification set and acquiring an instruction corresponding to the intent object; sending the instruction to the VR application, such that the VR application executes the instruction and feeds back an execution result.

Claims

1. A virtual reality speech control method applicable to a virtual reality device, comprising:

receiving, by a first application, a request for opening a speech interface sent initiatively by a second application installed in the virtual reality device, wherein, the first application is a voice control virtual reality system installed in the virtual reality device, the second application is a virtual reality application and the virtual reality device comprises the first application, a plurality of second applications and a virtual reality hardware device;

opening, by the first application, the speech interface in response to the request and sending, by the first application, an instruction for turning on a microphone to the virtual reality hardware device through the speech interface, such that the virtual reality hardware device turns on the microphone and receives speech information through the microphone;

receiving, by the first application, the speech information sent by the virtual reality hardware device through the speech interface;

converting, by the first application, the speech information to text information, and normalizing, by the first application, the text information to generate an intent object in conformity with a preset specification, wherein the speech information comprises a long command for invoking a virtual reality application and corresponds to the generated intent object;

recognizing, by the first application, the intent object based on a preset specification set to acquire an instruction corresponding to the intent object, the preset specification set comprising intent objects and instructions, the intent objects having one-to-one correspondence with the instructions, wherein, the instruction corresponding to the intent object comprises short commands, wherein each of the short commands is denoted by one or two words and wherein a short command is capable of controlling execution operations across two or more virtual reality applications;

determining a present scenario; and

when the present scenario is a preset scenario, sending, by the first application, one short command from short commands corresponding to the speech information to the second application after receiving the speech information, such that the second application executes the short command and feeds back an execution result, in which, the preset scenario is a scenario in a virtual reality environment where an action is achieved by the short command from the short commands corresponding to the speech information.

2. The method according to claim 1, wherein, the short commands include commands to start, stop, or confirm execution of the virtual reality application.

3. The method according to claim 1, wherein, the long commands include calling requests, message sending, payment, information searching, appointing events, and movement commands.

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

when the long command corresponding to the speech information is appointing an event, determining whether it arrives to an appointed time of the appointed event;

when it arrives to the appointed time, sending the long command corresponding to the appointed event to the second application, such that the second application executes the long command.

5. A virtual reality speech control apparatus applicable to a virtual reality device, comprising:

one or more processors; and

a memory, configured to store one or more software modules executable by the one or more processors,

wherein the one or more software modules comprises;

a receiving module, configured to receive a request for opening a speech interface sent initiatively by a second application installed in the virtual reality device, and to receive speech information sent by a virtual reality hardware device through the speech interface, wherein, the virtual reality device comprises a first application, a plurality of second applications and the virtual reality hardware device;

a control module, configured to open the speech interface in response to the request and receive the speech information through the speech interface, and to send an instruction for turning on a microphone to the virtual reality hardware device through the speech interface, such that the virtual reality hardware device turns on the microphone and receives the speech information through the microphone;

a generating module, configured to convert the speech information to text information, and normalize the text information to generate an intent object in conformity with a preset specification, wherein the speech information comprises a long command for invoking a virtual reality application and corresponds to the generated intent object;

an acquiring module, configured to recognize the intent object based on a preset specification set to acquire an instruction corresponding to the intent object, the preset specification set comprising intent objects and instructions, the intent objects having one-to-one correspondence with the instructions, wherein, the instruction corresponding to the intent object comprises short commands, wherein each of the short commands is denoted by one or two words and wherein a short command is capable of controlling execution operations across two or more virtual reality applications;

a first determining module, configured to determine a present scenario; and

a sending module, configured to, when the present scenario is a preset scenario, send one short command from the short commands corresponding to the speech information to the second application after receiving the speech information, such that the second application executes the short command and feeds back an execution result, in which, the preset scenario is a scenario in the VR environment where an action is achieved by the short command from the short commands corresponding to the speech information.

6. The apparatus according to claim 5, wherein the short commands include commands to start, stop, or confirm execution of the virtual reality application.

7. The apparatus according to claim 5, wherein, the long commands include calling requests, message sending, payment, information searching, appointing events, and movement commands.

8. The apparatus according to claim 5, further comprising:

a second determining module, configured to determine whether it arrives to an appointed time of an appointed event, when the long command corresponding to the speech information is appointing the event;

the sending module is further configured to send the long command corresponding to the appointed event to the second application when it arrives to the appointed time, such that the second application executes the long command.

9. A non-transitory computer-readable storage medium, configured to store one or more programs that, when executed by a processor of a terminal, cause the terminal to perform a virtual reality speech control method, the method comprising:

receiving, by a first application, a request for opening a speech interface sent initiatively by a second application installed in the virtual reality device, wherein, the first application is a voice control virtual reality system installed in the virtual reality device, the second application is a virtual reality application, and the virtual reality device comprises the first application, a plurality of second applications and a virtual reality hardware device;

opening, by the first application, the speech interface in response to the request and sending, by the first application, an instruction for turning on a microphone to the virtual reality hardware device through the speech interface, such that the virtual reality hardware device turns on the microphone and receives speech information through the microphone;

receiving, by the first application, the speech information sent by the virtual reality hardware device through the speech interface;

converting, by the first application, the speech information to text information, and normalizing the text information to generate an intent object in conformity with a preset specification, wherein the speech information comprises a long command for invoking a virtual reality application and corresponds to the generated intent object;

recognizing, by the first application, the intent object based on a preset specification set to acquire an instruction corresponding to the intent object, the preset specification set comprising intent objects and instructions, the intent objects having one-to-one correspondence with the instructions, wherein, the instruction corresponding to the intent object comprises short commands, wherein each of the short commands is denoted by one or two words and wherein a short command is capable of controlling execution operations across two or more virtual reality applications;

determining a present scenario; and

when the present scenario is a preset scenario, sending, by the first application, one short command from short commands corresponding to the speech information to the second application after receiving the speech information, such that the second application executes the short command and feeds back an execution result, in which, the preset scenario is a scenario in a virtual reality environment where an action is achieved by the short command from the short commands corresponding to the speech information.