WO2020062351A1

WO2020062351A1 - Speech recognition decoder and speech operating system

Info

Publication number: WO2020062351A1
Application number: PCT/CN2018/110530
Authority: WO
Inventors: 刘盛荣
Original assignee: 深圳市易控迪智能家居科技有限公司
Priority date: 2018-09-27
Filing date: 2018-10-16
Publication date: 2020-04-02
Also published as: CN108986823A

Abstract

A speech recognition decoder and a speech operating system. A speech input device (321) of the speech recognition decoder is electrically connected to an information comparison module (312), and the information comparison module (312) is electrically connected to a storage module (311) and a control module (313); the control module (313) is electrically connected to a controller (310), and the controller (310) is electrically connected to an operation device (330). The speech recognition decoder also has a wakeup function and a display module (3221; 3222; 3223) for indicating the working state of the speech recognition decoder. The speech input device receives external operation speech information; the information comparison module compares the operation speech information to pre-saved information in the storage module and generates a first comparison information result; and when the first comparison information result indicates that the information are the same, the control module transmits an operation signal of the operation speech information to the controller, and the controller controls the operation device to perform an operation of the operation signal. The present speech recognition decoder does not need to rely on a network, and by means of locally transmitting information, the response speed is fast, so that the controller indirectly has a speech reception function.

Description

Speech recognition decoder and speech operating system

Cross-reference to related applications

This application claims priority from a Chinese patent application filed with the Chinese Patent Office on September 27, 2018 under the application number 2018111357326 and entitled "A Voice Recognition Decoder and Voice Operating System", the entire contents of which are incorporated herein by reference. Applying.

Technical field

The present application relates to the technical field of speech recognition, and in particular, to a speech recognition decoder and a speech operating system.

Background technique

The prior art network version of the speech recognition system has a large system, high development and use costs, transmission of voice information through the network, delay in response, and use in different network environments due to the impact of the network environment. Transmission speed is affected.

Summary of the Invention

One of the objectives of the present application is to provide a speech recognition decoder that does not need to rely on a network, transmits information locally, has a fast response speed, and enables the controller to have a speech receiving function indirectly.

Another object of the present application is to provide a voice operating system, which uses the above-mentioned voice recognition decoder without relying on a network, transmits information locally through the system, has a fast response speed, and enables the controller to have a voice receiving function indirectly.

This application is implemented using the following technical solutions:

A speech recognition decoder including a controller, a speech receiver and an operating device;

The voice receiver includes a voice input device, a storage module, an information comparison module, and a control module;

The voice input device is electrically connected to the information comparison module, the information comparison module is electrically connected to the storage module and the control module, the control module is electrically connected to the controller, and the controller is electrically connected to the operation device;

The voice input device is configured to receive external operating voice information and pass the operating voice information to the information comparison module. The information comparison module compares the operating voice information with the pre-stored information in the storage module to generate a first comparison information result. And sending the first comparison information result to the control module;

When the first comparison information result is the same, the control module sends an operation signal for operating the voice information to the controller, and the controller controls the operation device to perform the operation of the operation signal.

Optionally, in the embodiment of the present application, the voice receiver further includes a display device, and the display device is electrically connected to the control module;

The voice input device is configured to receive the external display voice information and pass the display voice information to the information comparison module. The information comparison module compares the display voice information with the pre-stored information in the storage module to generate a second comparison information result. And sending the second comparison information result to the control module;

When the results of the second comparison information are the same, the control module controls the display device to perform display for displaying the voice information.

Optionally, in the embodiment of the present application, the display device includes a wake-up indicator, the wake-up indicator is connected to the control module, and the module controls the wake-up when the second comparison information result is the same The indicator lights up.

Optionally, in the embodiment of the present application, the display device includes a response indicator, the response indicator is connected to the control module, and the module controls the response when the first comparison information result is the same. The indicator lights up.

Optionally, in the embodiment of the present application, the display device includes a speaker, and the speaker is connected to the control module, and the module controls the speaker to issue a prompt voice message when the first comparison information result is the same. .

Optionally, in the embodiment of the present application, the voice receiver further includes a casing, and the voice input device and the display device are both disposed in the casing.

Optionally, in the embodiment of the present application, the above-mentioned case includes an upper case and a lower case, and the upper case cover is mounted on the lower case;

The display device includes a speaker, a wake-up indicator and a response indicator. The speaker, the wake-up indicator and the response indicator are all electrically connected to the control module. The upper case is provided with a speaker, and the connection between the upper case and the lower case is provided with a wake-up indicator and voice input. Unit and answer light.

Optionally, in the embodiment of the present application, the housing has a first end and a second end opposite to each other. The first end is electrically connected to the control module through a wire, and the second end is provided with a voice input device, a wake-up indicator, and a response. Light.

Optionally, in the embodiment of the present application, the voice receiver further includes a dial switch, the dial switch is electrically connected to the storage module, and the dial switch is configured to switch the storage module and display voice The wake-up word in the pre-stored message that the message is compared with.

Optionally, in the embodiment of the present application, the dial switch is installed on the lower case.

Optionally, in the embodiment of the present application, the upper case is recessed in a direction away from the lower case, the lower case is recessed in a direction away from the upper case, and the dial switch is disposed on a side of the lower case remote from the upper case.

Optionally, in the embodiment of the present application, the case further includes a mounting base, and the mounting base is detachably connected to a side of the lower case remote from the upper case, so that the dial switch is located between the lower case and the mounting base.

Optionally, in the embodiment of the present application, the mounting base is a smooth mounting plate.

A voice operating system includes a power module, a hand controller and the above-mentioned voice recognition decoder, and the power module and the hand controller are electrically connected to the control module.

Optionally, in the embodiment of the present application, the power module and the hand controller are respectively and detachably electrically connected to the speech recognition decoder through a connection cable.

Compared with the prior art, one of the beneficial effects of the speech recognition decoder provided in the embodiments of the present application includes: pre-stored information is pre-stored in the storage module, and the information obtained by the voice input device only needs to be compared with the pre-stored information. The control module controls the corresponding operating devices for operation. All information transmission and processing is performed inside the speech recognition decoder. It does not need to be transmitted through the network. The information is transmitted locally, responding quickly, meeting customer needs, and enabling control. The device has a voice receiving function indirectly.

One of the beneficial effects of the voice operating system provided by the embodiments of the present application includes: using the above-mentioned voice recognition decoder, without relying on the network, transmitting information through the local, responding fast, meeting customer needs, and enabling the controller to have voice reception indirectly Features.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solution of the embodiments of the present application more clearly, the drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, so It should be regarded as a limitation on the scope. For those of ordinary skill in the art, other creative drawings can also be obtained according to these drawings without any creative work, which also belongs to the protection scope of the present application.

FIG. 1 is a schematic structural diagram of a voice operating system according to an embodiment of the present application;

2 is a schematic block diagram of a speech recognition decoder in a speech operating system provided by an embodiment of the present application;

3 is a first schematic structural diagram of a voice receiver in a voice operating system according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a second structure of a voice receiver in a voice operating system provided by an embodiment of the present application.

Icons: 100-power module; 200-hand controller; 300-voice recognition decoder; 110-power converter; 120-power plug; 310-controller; 320-voice receiver; 330-operating device; 321-voice Input device; 322-display device; 323-shell; 324-dip switch; 311-storage module; 312-information comparison module; 313-control module; 3221-speaker; 3222-wake indicator light; 3223-response indication Lamp; 3231-upper shell; 3232-lower shell; 3233-first end; 3234-second end.

detailed description

In order to make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments These are part of the embodiments of the present application, but not all the embodiments. The components of embodiments of the present application, which are generally described and illustrated in the drawings herein, may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

It should be noted that similar reference numerals and letters indicate similar items in the following drawings, so once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

Examples

Referring to FIG. 1, the voice operating system includes a power module 100, a hand controller 200, and a voice recognition decoder 300. The power module 100 and the hand controller 200 are electrically connected to the voice recognition decoder 300, respectively. Power is provided to the entire voice operating system through the power module 100 so that other components can operate.

In this embodiment, the power module 100 includes a power converter 110 and a power plug 120. The power converter 110 and the power plug 120 are electrically connected by a wire. The power plug 120 is configured to be installed on a socket, and the power is converted into electrical energy by the power converter 110. Power that can be used by the hand controller 200 and the speech recognition decoder 300.

Optionally, in this embodiment, the power module 100 and the hand controller 200 are detachably and electrically connected to the speech recognition decoder 300 through a connection cable, respectively.

The principle and structure of the power converter 110 are prior art, which will not be described in detail in this embodiment.

In this embodiment, the speech recognition decoder 300 includes a controller 310, a speech receiver 320, and an operation device 330. Since the voice receiver 320 is electrically connected to the controller 310, the ordinary controller 310 has a function of receiving voice indirectly.

Referring to FIG. 2, in this embodiment, the voice receiver 320 includes a voice input device 321, a display device 322, a housing 323, a dial switch 324, a storage module 311, an information comparison module 312, and a control module 313.

The display device 322 is electrically connected to the control module 313. The display device 322 includes a speaker 3221, a wake-up indicator 3222, and a response indicator 3223. The speaker 3221, the wake-up indicator 3222, and the response indicator 3223 are electrically connected to the control module 313. A voice input device 321 is electrically connected to the information comparison module 312, the information comparison module 312 is electrically connected to the storage module 311 and the control module 313, the control module 313 is electrically connected to the controller 310, and the controller 310 is electrically connected to the operation device 330.

Optionally, the voice input device 321 may be configured to receive the input display voice information and pass the display voice information to the information comparison module 312. The information comparison module 312 compares the display voice information with the pre-stored information in the storage module 311. To generate a second comparison information result and send the second comparison information result to the control module 313; when the second comparison information result is that the displayed voice information is the same as the pre-stored information, the control module 313 controls the display device 322 to execute the displayed voice Information display.

The voice input device 321 may be a microphone or a microphone, and can receive voice information. The pre-stored information in the storage module 311 includes a wake-up instruction. Generally, the wake-up instruction is the name of a device that the voice operating system needs to control, such as a sofa, a chair, a bed, and the like. The wake-up indicator 3222 may be configured to indicate whether the second comparison result is the same by emitting light.

After the voice operating system is connected, the user enters the word "sofa" into the voice input device 321, and the voice input device 321 transmits it to the information comparison module. The information comparison module 312 compares the "sofa" with the pre-stored information in the storage module 311. Compare, generate the second comparison result, and send the second comparison result to the control module 313. If the "sofa" entered by the user is consistent with the "sofa" pre-stored in the storage module 311, the second comparison result is the same , The entire voice operating system wakes up successfully, and the control module 313 controls the wake-up indicator light 3222 to emit light. If the "sofa" entered by the user is not consistent with the information pre-stored in the storage module 311, and the second comparison result is different, the wake-up indicator 3222 is off.

Optionally, the voice input device 321 may be configured to receive the input operation voice information and pass the operation voice information to the information comparison module 312. The information comparison module 312 compares the operation voice information with the pre-stored information in the storage module 311. To generate a first comparison information result and send the first comparison information result to the control module 313; when the first comparison information result is that the operation voice information is the same as the pre-stored information, the control module 313 sends an operation signal to operate the voice information Sent to the controller 310, the controller 310 controls the operation device 330 to perform an operation of an operation signal.

The pre-stored information in the storage module 311 also includes operation information. Taking the sofa as an example, the pre-stored information in the storage module 311 can also be: open the sofa and retract the sofa; open the headrest and retract the headrest; open the lumbar support and retract the lumbar support; Open all and retract all; open a little, retract a little; turn on the cushion heating, turn off the cushion heating; TV mode, reading mode, rest mode; and other voice commands.

After the wake-up by the voice operating system is successful, that is, after the user finds that the wake-up indicator 3222 is on, the user may continue to input operation voice information through the voice input device 321, so that the operation device 330 performs a corresponding operation. Specifically, after the user finds that the wake-up indicator light 3222 is on, the user can continue to input the "open sofa" instruction through the voice input device 321, and the voice input device 321 transmits it to the information comparison module, and the information comparison module 312 sends the "open sofa" and The pre-stored information in the storage module 311 is compared to generate a first comparison result, and the first comparison result is sent to the control module 313. If the "open sofa" input by the user is in phase with the "open sofa" pre-stored in the storage module 311, If they match, the first comparison result is the same, and the control module 313 controls the operation device 330 to perform an operation of opening the sofa. If the “open sofa” input by the user is inconsistent with the information stored in the storage module 311 and the first comparison result is different, the operation device 330 will not perform the operation of opening the sofa.

At the same time, when the first comparison result is the same, the control module 313 controls the response indicator light 3223 to light up or the speaker 3221 to send out a voice message prompting to "open the sofa", so that the user knows that the user has input a valid voice message. It should be noted that: the response indicator 3223 flashes once when receiving a valid voice message; and the wake-up indicator 3222 is always on when the voice operating system wakes up. When the first comparison result is different, the response indicator 3223 is off, and the speaker 3221 does not emit a sound.

The transmission and processing of the above information are all performed inside the speech recognition decoder 300, and do not need to be transmitted through the network. The information is transmitted locally, the response speed is fast, and the needs of the customer are met.

The voice receiver 320 further includes a housing 323, and the voice input device 321, the dial switch 324, and the display device 322 are all disposed in the housing 323.

Optionally, please refer to FIG. 3 and FIG. 4. In this embodiment, the casing 323 includes an upper casing 3231 and a lower casing 3232. The upper casing 3231 is covered by the lower casing 3232. The upper casing 3231 is provided with a speaker 3221 and the upper casing 3231. A wake-up indicator 3222, a voice input device 321, and a response indicator 3223 are provided at the connection point with the lower case 3232.

The speaker 3221 is disposed on the upper case 3231, and is convenient for emitting sound through the speaker 3221, so that the user can clearly receive the voice information from the speaker 3221. A wake-up indicator 3222, a voice input device 321, and a response indicator 3223 are provided at the connection between the upper case 3231 and the lower case 3232, which is convenient for setting and observation.

Optionally, the housing 323 has a first end 3233 and a second end 3234 opposite to each other. The first end 3233 is electrically connected to the control module 313 through a wire, the first end 3233 is electrically connected to the controller 310 through a wire, and the second end is 3234 sets a voice input device 321, a wake-up indicator 3222, and a response indicator 3223 to facilitate the input of voice by the voice input device 321, and also facilitates the observation of the wake-up indicator 3222 and then the response indicator 3223.

The DIP switch 324 is installed in the lower case 3232. The DIP switch 324 is electrically connected to the storage module 311. By switching the DIP switch 324, different wake-up words can be switched. For example, when the DIP switch 324 is displayed in the first gear, it wakes up. When the dial switch 324 is in the second gear, the wake-up word is "two"; when the dial switch 324 is in the third gear, the wake-up word is "three" and so on. By setting different wake-up words to wake up the voice operating system, it is convenient to independently operate one or more of several controllers installed in the same area.

Optionally, in this embodiment, the housing 323 further includes a mounting base. The upper case 3231 is recessed toward the direction away from the lower case 3232, the lower case 3232 is recessed toward the upper case 3231, and the dial switch 324 is disposed on the lower case 3232. The side away from the upper case 3231, the mounting base is detachably connected to the side away from the upper case 3231 of the lower case 3232, so that the dial switch 324 is located between the lower case 3232 and the installation base.

In order to set the various components on the housing 323, the mounting base can be removed, and the dialing of the dial switch 324 can be performed. After the dialing is completed, the mounting base is installed to avoid accidental dialing. The mounting base is a smooth mounting plate, which is convenient for the voice receiver 320 to be placed in different positions. The mounting base can be connected to the lower case 3232 by screws, which facilitates the installation and setting of the entire voice receiver 320.

Optionally, in this embodiment, the voice receiver 320 and the controller 310 are set by a wire and a connector connected to the wire, that is, a wire is provided on the voice receiver 320, and an end of the wire is remote from the voice receiver 320. There are connectors. When it is necessary to make the ordinary controller 310 have a voice expansion function, plug the connector into the jack of the controller 310; when it is not necessary to set the voice expansion function of the controller 310, remove the connector from the jack. take out.

Optionally, in this embodiment, the operation device 330 can also be controlled by the hand controller 200. The hand controller 200 is electrically connected to the control module 313 of the controller 310, and the user can directly operate the controller 200 to operate the device. The operation information is directly sent to the controller 310, and the controller 310 controls the operation device 330 to perform the operation. The working principle and structure of the hand controller 200 is the prior art, which is not described in detail in this embodiment. The voice operating system provided by this embodiment can not only perform operation control by voice, but also manual operation control, thereby increasing the use range.

The above description is only a preferred embodiment of the present application, and is not intended to limit the present application. For those skilled in the art, this application may have various modifications and changes. Any modification, equivalent replacement, or improvement made within the spirit and principle of this application shall be included in the protection scope of this application.

Industrial applicability

One of the beneficial effects of the speech recognition decoder provided by the embodiments of the present application includes: pre-stored information is pre-stored in the storage module, and the information obtained by the voice input device only needs to be compared with the pre-stored information, and the corresponding operation can be controlled by the control module. The device operates. All information is transmitted and processed inside the speech recognition decoder. It does not need to be transmitted through the network. The information is transmitted locally. The response speed is fast and the customer's needs are met. The controller has indirect voice reception. Features. One of the beneficial effects of the voice operating system provided by this application includes: using the above-mentioned voice recognition decoder, without relying on the network, transmitting information locally, responding fast, meeting customer needs, and enabling the controller to have a voice receiving function indirectly.

Claims

A speech recognition decoder, comprising a controller, a speech receiver and an operating device;

The voice receiver includes a voice input device, a storage module, an information comparison module, and a control module;

The voice input device is electrically connected to the information comparison module, the information comparison module is electrically connected to the storage module and the control module, the control module is electrically connected to the controller, and the controller Electrically connected to the operating device;

The voice input device is configured to receive external operation voice information and pass the operation voice information to an information comparison module, and the information comparison module compares the operation voice information with pre-stored information in the storage module. Yes, generate a first comparison information result, and send the first comparison information result to the control module;

When the results of the first comparison information are the same, the control module sends an operation signal of the operation voice information to the controller, and the controller controls the operation device to perform an operation of the operation signal.
The speech recognition decoder according to claim 1, wherein the speech receiver further comprises a display device, and the display device is electrically connected to the control module;

The voice input device is configured to receive external display voice information, and pass the display voice information to an information comparison module, and the information comparison module compares the display voice information with pre-stored information in the storage module. Yes, generate a second comparison information result, and send the second comparison information result to the control module;

When the results of the second comparison information are the same, the control module controls the display device to perform the display of the display voice information.
The speech recognition decoder according to claim 2, wherein the display device comprises a wake-up indicator light, the wake-up indicator light is connected to the control module, and the module has a phase comparison result in the second comparison information. At the same time, the wake-up indicator is controlled to emit light.
The speech recognition decoder according to claim 2, wherein the display device comprises a response indicator light, the response indicator light is connected to the control module, and the module has a phase comparison result in the first comparison information. At the same time, the response indicator light is controlled to light up.
The speech recognition decoder according to claim 2, wherein the display device includes a speaker, and the speaker is connected to the control module, and the module controls the control unit when the first comparison information result is the same. The speaker sends a prompt voice message.
The speech recognition decoder according to any one of claims 2 to 5, wherein the speech receiver further comprises a casing, and the speech input device and the display device are both disposed in the casing.
The speech recognition decoder according to claim 6, wherein the casing comprises an upper casing and a lower casing, and the upper casing is mounted on the lower casing;

The display device includes a speaker, a wake-up indicator and a response indicator. The speaker, the wake-up indicator and the response indicator are all electrically connected to the control module. The upper shell is provided with the speaker. The connection between the upper case and the lower case is provided with the wake-up indicator, the voice input device and the response indicator.
The speech recognition decoder according to claim 7, wherein the housing has a first end and a second end opposite to each other, and the first end is electrically connected to the control module through a wire, and the first The two ends are provided with the voice input device, the wake-up indicator and the response indicator.
The speech recognition decoder according to claim 7 or 8, wherein the speech receiver further comprises a dial switch, the dial switch is electrically connected to the storage module, and the dial switch is configured to switch The storage module compares the wake-up word in the pre-stored information with the displayed voice information.
The speech recognition decoder according to claim 9, wherein the dial switch is mounted on the lower case.
The speech recognition decoder according to claim 9 or 10, wherein the upper case is recessed in a direction away from the lower case, the lower case is recessed in a direction toward the upper case, and the dial switch is It is arranged on a side of the lower shell far from the upper shell.
The speech recognition decoder according to any one of claims 9 to 11, characterized in that the housing further comprises a mounting base, and the mounting base is detachably connected to the lower case away from the upper case. On one side, the dial switch is located between the lower case and the mounting base.
The speech recognition decoder according to claim 12, wherein the mounting base is a smooth mounting plate.
A voice operating system, comprising a power module, a hand controller and the voice recognition decoder according to any one of claims 1-13, the power module and the hand controller and the voice recognition decoding The devices are all electrically connected.
The voice operating system according to claim 14, wherein the power module and the hand controller are respectively and detachably electrically connected to the voice recognition decoder through a connection cable.