CN117809661A - Display device and wake-up word reading method - Google Patents

Abstract

The application provides a display device and a method for capturing wake-up words. The display device responds to the collar reading starting operation of the user, and displays a guide page of the wake-up word, wherein the guide page comprises a collar reading button of the wake-up word. The display device responds to a collar reading instruction input by a user based on the collar reading button, plays collar reading voice of the wake-up word, displays a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluates a result display area. When receiving learning voice input by a user, the display device compares the learning voice with the collar-read voice to obtain an evaluation result of the user reading wake-up words, and displays the evaluation result in an evaluation result display area. The user can start the collar-read mode at any time to learn the pronunciation of the wake-up word, and can master the accuracy of the user to the pronunciation of the wake-up word based on the evaluation result.

Description

Display device and wake-up word reading method

Technical Field

The application relates to the technical field of display equipment, in particular to a display equipment and a method for capturing and reading wake-up words.

Background

The display device refers to a terminal device capable of outputting a specific display screen, and may be a terminal device such as a smart television, a mobile terminal, a smart advertisement screen, and a projector. Taking intelligent electricity as an example, the intelligent television is based on the Internet application technology, has an open operating system and a chip, has an open application platform, can realize a bidirectional man-machine interaction function, and is a television product integrating multiple functions of video, entertainment, data and the like, and the intelligent television is used for meeting the diversified and personalized requirements of users.

The display device is configured with a far-field speech control function that is turned on after recognizing speech of a Wake word (Wake word) input by a user. When the display device is set for the first time, a guiding process of the wake-up word is provided for the user, namely, the user is enabled to know the pronunciation of the wake-up word by playing the standard voice of the wake-up word. However, the user cannot know whether the pronunciation of the wake-up word is accurate or not, and cannot start the guidance process of the wake-up word at any time after the display device is first started.

Disclosure of Invention

The application provides display equipment and a method for capturing and reading wake-up words, so as to provide the opportunity for a user to learn the pronunciation of the wake-up words at any time and inform the user of the accuracy of the pronunciation of the wake-up words.

In a first aspect, the present application provides a display device, including:

a controller configured to:

responding to a starting instruction of a user, and controlling a display to display a guide page of a wake-up word, wherein the guide page comprises a read-out button of the wake-up word;

responding to a collar reading instruction input by a user based on the collar reading button, playing collar reading voice of the wake-up word, controlling the display to display a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluating a result display area;

When learning voice input by a user is received, comparing the learning voice with the collar-read voice to obtain an evaluation result of the wake-up word read by the user;

and controlling the display to display the evaluation result in the evaluation result display area.

In some embodiments of the present application, before the controller responds to the collar-read start operation of the user and controls the display to display the guide page of the wake-up word, the controller is configured to:

and if the starting instruction is an instruction input by a user for starting a microphone switch, responding to the starting instruction, controlling the display to display the guide page in a popup window mode, and displaying the read-in button in the popup window.

In some embodiments of the present application, the controller, in response to a start instruction of a user, controls the display to display a guidance page of a wake-up word, and is configured to:

and if the starting instruction is an instruction input by a user selecting a hands-free mode option in a voice assistant menu, controlling the display to display the guide page in response to the starting instruction, wherein the guide page comprises content related to the wake-up word and the read-out button.

In some embodiments of the present application, the controller is configured to, in response to a collar reading instruction input by a user based on the collar reading button, play a collar reading voice of the wake-up word, control the display to display a collar reading prompt of the wake-up word in a popup window form in the guide page, and an evaluation result display area, where the evaluation result display area is configured to:

switching a voice control mode from a control mode to a read-in mode, closing a channel for not playing the read-in voice, and adjusting a threshold value for judging a wake-up value of the wake-up word from a first threshold value to a second threshold value, wherein the wake-up value is used for representing the similarity degree of the received voice and the standard pronunciation of the wake-up word, and the lower the threshold value of the wake-up value is, the easier the received voice is judged as the wake-up word;

and in the read-in mode, the controller recognizes the wake-up word input by the user as learning voice, the control mode corresponds to the first threshold value, the read-in mode corresponds to the second threshold value, and the second threshold value is lower than the first threshold value.

In some embodiments of the present application, the controller is configured to, in response to a collar reading instruction input by a user based on the collar reading button, play a collar reading voice of the wake-up word, control the display to display a collar reading prompt of the wake-up word in a popup window form in the guide page, and an evaluation result display area, where the evaluation result display area is configured to:

detecting whether a focus is positioned on the collar reading button or not when the collar reading voice of the wake-up word is played;

and stopping playing the collar-reading voice of the wake-up word if the focus is detected to leave the collar-reading button.

In some embodiments of the present application, the controller is configured to, in response to a collar reading instruction input by a user based on the collar reading button, play a collar reading voice of the wake-up word, control the display to display a collar reading prompt of the wake-up word in a popup window form in the guide page, and an evaluation result display area, where the evaluation result display area is configured to:

if receiving a read command input by the user based on the read button again when playing the read voice of the wake-up word, responding to the read command input again, and playing the read voice of the wake-up word again.

In some embodiments of the present application, the controller continuously plays the collar-read voice of the wake-up word N times, where N is a positive integer greater than 0, the controller, in response to a collar-read instruction input by a user based on the collar-read button, plays the collar-read voice of the wake-up word, and controls the display to display a collar-read prompt of the wake-up word in a popup window form in the guide page, and the evaluation result display area is configured to:

If the learning voice is received in the process of playing the N times of the leading voice of the wake-up word, and the learning voice is recognized to contain the wake-up word, stopping playing the leading voice of the wake-up word, and playing a prompt tone indicating that the wake-up word is recognized.

In some embodiments of the present application, when receiving a learning voice input by a user, the controller compares the learning voice with the collar-read voice to obtain an evaluation result that the user follows the wake-up word, and is configured to:

converting the learning voice into a corresponding wake-up value according to a preset algorithm;

and determining the evaluation result corresponding to the converted wake-up value according to the corresponding relation between the wake-up value and the evaluation result.

In some embodiments of the present application, the controller controls the display to display the evaluation result within the evaluation result display area, and is further configured to:

when the display duration of the evaluation result is equal to a duration threshold, closing the popup window, switching the voice control mode from the read-in mode to the control mode, opening a channel for not playing the read-in voice, and adjusting a threshold for judging the wake-up value of the wake-up word from the second threshold to the first threshold.

In a second aspect, the present application further provides a method for reading a wake-up word, which is applied to the display device according to any one of the first aspect;

the method comprises the following steps:

responding to a starting instruction of a user, displaying a guide page of a wake-up word, wherein the guide page comprises a read-out button of the wake-up word;

responding to a collar reading instruction input by a user based on the collar reading button, playing collar reading voice of the wake-up word, displaying a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluating a result display area;

when learning voice input by a user is received, comparing the learning voice with the collar-read voice to obtain an evaluation result of the wake-up word read by the user;

and displaying the evaluation result in an evaluation result display area.

The display device responds to the collar reading starting operation of the user, and displays a guide page of the wake-up word, wherein the guide page comprises a collar reading button of the wake-up word. The display device responds to a collar reading instruction input by a user based on the collar reading button, plays collar reading voice of the wake-up word, displays a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluates a result display area. When receiving learning voice input by a user, the display device compares the learning voice with the collar-read voice to obtain an evaluation result of the user reading wake-up words, and displays the evaluation result in an evaluation result display area. The user can start the collar-read mode at any time to learn the pronunciation of the wake-up word, and can master the accuracy of the user to the pronunciation of the wake-up word based on the evaluation result.

Drawings

In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.

Fig. 1 is a usage scenario of a display device according to an embodiment of the present application;

fig. 2 is a block diagram of a configuration of a control device in an embodiment of the present application;

fig. 3 is a configuration diagram of a display device in an embodiment of the present application;

fig. 4 is an operating system configuration diagram of a display device according to an embodiment of the present application;

fig. 5 is a schematic flow chart of a display device for capturing a wake-up word in an embodiment of the present application;

FIG. 6 is a schematic diagram of a guide page displayed in a pop-up window according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a guide page displayed in the form of a page in an embodiment of the present application;

FIG. 8 is a logic judgment diagram of a process of playing a read-ahead voice by a display device according to an embodiment of the present application;

fig. 9 is a schematic flow chart of a display device identifying learning intention of a user in an embodiment of the present application;

fig. 10 is a schematic diagram of a display device displaying a collar reading prompt in a guide page displayed in a popup window according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a display device displaying a collar reading prompt in a guide page displayed in the form of a page in an embodiment of the present application;

fig. 12 is a schematic flow chart of a display device calculating an evaluation result in the embodiment of the present application;

FIG. 13 is a diagram illustrating a transition diagram of wake-up values and evaluation results according to an embodiment of the present disclosure;

fig. 14 is a schematic diagram of a display device displaying an evaluation result in a guide page displayed in a popup window in the embodiment of the present application;

fig. 15 is a schematic diagram of a display device displaying an evaluation result in a guide page displayed in the form of a page in the embodiment of the present application;

fig. 16 is a logic judgment diagram of closing a pop-up window by a display device according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The embodiments described in the examples below do not represent all embodiments consistent with the present application. Merely as examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

It should be noted that the brief description of the terms in the present application is only for convenience in understanding the embodiments described below, and is not intended to limit the embodiments of the present application. Unless otherwise indicated, these terms should be construed in their ordinary and customary meaning.

The terms "first," second, "" third and the like in the description and in the claims and in the above-described figures are used for distinguishing between similar or similar objects or entities and not necessarily for limiting a particular order or sequence, unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances.

The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or apparatus that comprises a list of elements is not necessarily limited to all elements explicitly listed, but may include other elements not expressly listed or inherent to such product or apparatus.

The display device provided by the embodiment of the application can have various implementation forms, for example, can be a smart television, a laser projection device, a display (monitor), an electronic whiteboard (electronic bulletin board), an electronic desktop (electronic table) and the like, and can also be a device with a display screen, such as a mobile phone, a tablet computer, a smart watch and the like. Fig. 1 and 2 are specific embodiments of a display device of the present application.

Fig. 1 is a schematic view of a usage scenario of a display device according to an embodiment. As shown in fig. 1, a user may operate the display apparatus 200 through the control apparatus 100, and the display apparatus 200 may acquire network data through the server 300 or acquire a live signal through a satellite.

Fig. 2 is a block diagram of the configuration of the control apparatus 100. In some embodiments, the control device 100 may be a remote controller, and the communication between the remote controller and the display device 200 may include at least one of infrared protocol communication or bluetooth protocol communication, and other short-range communication modes, and the display device 200 may be controlled by a wireless or wired mode. The user may control the display device 200 by inputting user instructions through keys on a remote control, voice input, control panel input, etc.

Fig. 3 shows a block diagram of a configuration of the display device 200 in accordance with an exemplary embodiment.

The display apparatus 200 includes at least one of a modem 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface 280.

In some embodiments, the display apparatus 200 may establish transmission and reception of control signals and data signals with the control apparatus 100 or the server 400 through the communicator 220. In some embodiments, the controller 250 and the modem 210 may be located in separate devices, i.e., the modem 210 may also be located in an external device to the main device in which the controller 250 is located, such as an external set-top box or the like. In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored on the memory. The controller 250 controls the overall operation of the display apparatus 200. In some embodiments, the controller 250 includes at least one of a central processing unit (Central Processing Unit, CPU), a video processor, an audio processor, a graphics processor (Graphics Processing Unit, GPU), RAM (Random Access Memory), a ROM (Read-Only Memory), a first to nth interface for input/output, a communication Bus (Bus), and the like. In some embodiments, the display 260 includes a display screen component for presenting a picture, and a driving component for driving an image display, a component for receiving an image signal output from the controller 250, displaying video content, image content, and a menu manipulation interface, and a user manipulation UI interface. In some embodiments, the display 260 may be a liquid crystal display, an OLED display, a projection device, and a projection screen. In some embodiments, a user may input a user command through a graphical user interface (Graphic User Interface, GUI) displayed on the display 260, and the user input interface receives the user input command through the Graphical User Interface (GUI). Alternatively, the user may input the user command by inputting a specific sound or gesture, and the user input interface recognizes the sound or gesture through the sensor to receive the user input command. In some embodiments, a "user interface" is a media interface for interaction and exchange of information between an application or operating system and a user that enables conversion between an internal form of information and a form acceptable to the user. A commonly used presentation form of a user interface is a Graphical User Interface (GUI), which refers to a user interface related to computer operations that is displayed in a graphical manner. It may be an interface element such as an icon, a window, a control, etc. displayed in a display screen of the electronic device, where the control may include at least one of a visual interface element such as an icon, a button, a menu, a tab, a text box, a dialog box, a status bar, a navigation bar, a Widget, etc.

In some embodiments, the display device 200 is based on a VIDAA software platform, and as shown in fig. 4, the Linux platform-based operating system is divided into three layers, namely, an application layer, a middleware layer and a hardware layer from top to bottom. The application layer comprises various applications and application frameworks. The middleware layer includes various protocols and components. The hardware layer includes various interfaces, hardware and drivers.

In some embodiments, a third party application is integrated on the display device 200 in addition to the Native application (Native App) to provide the user with richer functionality and resources through the third party application.

The display apparatus 200 is configured with a far-field voice control function, the display apparatus 200 turns on the far-field voice control function after recognizing the voice of the wake-up word input by the user, and the display apparatus 200 may perform a corresponding task in response to the voice instruction input by the user after turning on the far-field voice control function, thereby freeing up manual control by the user. The display device 200 provides a guidance process of wake-up words to the user when performing the first power-on setting. The guidance process is used to provide a process of learning the pronunciation of the wake-up word for the user, and the display device 200 makes the user learn the pronunciation of the wake-up word by playing the standard voice of the wake-up word. However, based on the guiding process, the user cannot know whether the pronunciation of the wake-up word is accurate or not, that is, cannot know the learning effect of learning the pronunciation of the wake-up word. Therefore, if the learning effect of the user is not ideal, the success rate of the user for subsequently using the wake-up word to start the far-field voice control function will be affected. Moreover, if the user finds that the pronunciation of the wake-up word is not ideal during the subsequent use of the display device 200, the user cannot start the guiding process of the wake-up word at any time, and learn the pronunciation of the wake-up word.

In order to solve the above-mentioned problems, the embodiments of the present application provide a method for capturing a wake-up word, according to which the display device 200 can provide a guiding process of the wake-up word for a user at any time, so that the user can develop and learn the pronunciation of the wake-up word at any time, and can feed back learning results for the user. The display device 200 may read the wake-up word according to the flow shown in fig. 5, and specifically includes the following steps:

s501, responding to a starting instruction of a user, and displaying a guide page of a wake-up word.

In some embodiments, the activation instruction may be an instruction for a user to turn on a microphone switch input of the display device 200. At this time, the microphone switch of the display device 200 is an entrance of the guide page.

The microphone switch may be configured on the display device 200, such as a power switch disposed outside the display device 200, and the microphone is powered up when the switch is in an on state and powered down when the switch is in an off state. The microphone switch may also be configured on the control device 100, such as a microphone key on the control device 100.

When the user needs to learn the pronunciation of the wake-up word, the starting instruction can be input at any time based on the microphone switch. For example, if the current microphone switch is in an off state, the user may input a start instruction by an operation of turning on the microphone switch. For another example, if the current microphone switch is in an on state, the user may turn off the microphone switch first and then input a start command by an operation of turning on the microphone switch.

The display apparatus 200 displays a guide page of the wake-up word, which includes a collar-read button, in a popup window form on the current page in response to an instruction to turn on the microphone switch. The popup window can be displayed at the lower part, the left side and the like of the current page. Taking the current page as the system home page shown in fig. 6 as an example, the system home page includes a main menu 601 displayed on the left side, and the main menu 601 may include user (Account), search, notification, input, settings, and Live TV (Live TV) options. The system main page also comprises application lists such as App1, app2, app3 and App4 displayed on the right side. In response to the start instruction, the display device 200 may display the guide page in the form of a pop-up window as shown in fig. 6, below the system main page, in the form of a display pop-up window 602, the pop-up window 602 including a collar button 603. The popup 602 also includes prompts related to the read wake word, such as "Say" Hey VIDAA "first, followed by the commend, how to Say VIDAA? ".

The guide page is displayed in a popup window mode, the influence on the display of the current page can be reduced, and a user can learn the pronunciation of the wake-up word through the guide page in the process of browsing the current page. For example, when a user views a drama through a live television, the user may input a start instruction by turning on a microphone switch when the user displays an advertisement for spot-cast, the display device 200 may display a guide page in a popup window form on the current page in response to the start instruction, and the user may learn pronunciation of a wake-up word based on the guide page, and may also pay attention to the play progress of the advertisement to avoid missing the drama.

In some embodiments, the launch instruction may be an instruction entered by the user based on a Hands-Free Mode option in a Voice Assistant (Voice Assistant) menu. The voice assistant menu is a next level menu corresponding to voice assistant options in a Settings menu, and the hands-free mode-associated page includes voice control-related content, such as wake-up word-related content. The difference between the page associated with the original hands-free mode is that a read-out button is added in the page associated with the hands-free mode in the embodiment of the application, so that the page associated with the hands-free mode has the function of providing pronunciation of a learning wake-up word and can be used as a guide page of the wake-up word. Thus, the hands-free mode option is to guide the entry of the page.

The voice assistant menu is entered from the setting menu, and then the operation path of the associated page in the hands-free mode is a relatively well-known operation path of the user, so that the hands-free mode is configured as an entrance of the guide page, the associated page in the hands-free mode is configured as the guide page, the user can more conveniently memorize and search the entrance of the guide page, and the experience of learning the pronunciation of the wake-up word by the user is improved.

The bootstrap page may present more specific content related to hands-free mode. In some embodiments, the wake word related content of the hands-free mode related content may be presented in the form of a wake word mixing component. The function and the operation method of the wake-up word can be described through text, and the collar reading function is provided through a collar reading button. The guide page may be used when a user needs to perform more specific and advanced settings for voice services, including learning of wake words, etc.

The process of displaying a guide page by the display device 200 is presented in connection with fig. 7. As shown in (1) of fig. 7 (differing from fig. 6 in that a focus is displayed on the setting option, and a focus is shown in black ground), the display apparatus 200 may display a setting menu 701 as shown in (2) of fig. 7 in response to a selection instruction input by the user based on the setting option within the main menu when the main menu 601 is displayed. The display apparatus 200 displays a Voice assistant menu 702 shown in fig. 7 (3) in response to a user selection instruction based on a Voice assistant option input in the setup menu, the Voice assistant menu 702 including Voice assistants such as VIDAA Voice, language (Language), hands-free mode options available for user selection.

The display apparatus 200 displays a guidance page as shown in (3) in fig. 7, including a switch 703 of the hands-free mode, in response to an instruction input by the user based on the hands-free mode option, and turns on the voice control service when the switch 703 is in an on state. The bootstrap page also includes a wake word component that includes text information, such as "handles-Free Mode used the microphone built into your TV, so you can Wake up voice services with the wake word" Hey VIDAA "," and "How to Say VIDAA? ". The bootstrap page also includes a collar button 704, such as a Commands sample button.

The collar read button in the guide page is used to initiate the collar read function. The collar button may be an icon button, a text button, or a button where an icon is combined with text.

S502, responding to a collar reading instruction input by a user based on a collar reading button, playing collar reading voice of the wake-up word, displaying a collar reading prompt of the wake-up word in a popup window mode in a guide page, and evaluating a result display area.

The user may enter a collar read instruction by selecting a collar read button in the guide page. For example, if the guide page is as shown in fig. 6, the user may input a collar reading instruction by selecting the collar reading button 603. As another example, if the guide page is as shown in fig. 7 (3), the user may input a collar reading instruction by selecting the collar reading button 704.

The display device 200 plays a read-in voice of the wake-up word in response to the read-in instruction, the read-in voice being a standard pronunciation of the wake-up word, and the user can learn and learn the standard pronunciation of the wake-up word by listening to the read-in voice.

An optimization is made for the process of playing the read-in voice of the wake-up word by the display device 200, such as the logic judgment diagram of the playing process shown in fig. 8.

The display device 200 is configured with a judgment process of the learning intention of the user.

The display device 200 may recognize the learning intention of the user according to the flow shown in fig. 9, specifically as follows:

s901, when the collar-read voice of the wake-up word is played, whether the focus is positioned on the collar-read button is detected.

The display device 200 may be configured with a judgment rule: if the focus is on the collar-read button, the user has the intention to learn the pronunciation of the wake-up word. If the focus leaves the collar-read button, the user does not have the intention to learn the pronunciation of the wake-up word.

Based on the above-mentioned judgment rule, the display device 200 detects in real time whether the focus is located on the collar-read button or not when the collar-read voice of the wake-up word is played, so as to judge whether the user has the intention of learning the pronunciation of the wake-up word or not.

S902, if the focus is detected to leave the collar-reading button, stopping playing the collar-reading voice of the wake-up word.

If the focus is detected to be positioned on the collar-reading button, the collar-reading voice of the wake-up word is normally played, so that the user can normally perform the learning process. If the focus is detected to leave the collar-reading button, stopping playing the collar-reading voice of the wake-up word so as to avoid affecting other operations of the user. The user may re-enter the read command based on the read button to re-start the read process.

In some embodiments, if the user does not input other instructions and the focus is returned to the collar-read button within a specified period of time, the display apparatus 200 may determine that the user has operated the focus away from the collar-read button as a malfunction, thereby automatically playing the collar-read voice of the wake-up word without the user having to input the collar-read instruction again based on the collar-read button.

The display device 200 is configured with a multiple button trigger prevention processing mechanism.

The display device 200 plays the read-in voice of the wake-up word in response to the read-in instruction input by the user based on the read-in button. When playing the collar-read voice of the wake-up word, if a collar-read instruction input by the user based on the collar-read button is received, the display device 200 stops playing the collar-read voice of the wake-up word of the current round in response to the re-input collar-read instruction, and replays the collar-read voice of the wake-up word.

In some embodiments, the display device 200 is configured to play the read-ahead speech of the wake-up word N times in succession, N being a positive integer greater than 0. When n=1, the display apparatus 200 stops playing the read-in voice if a read-in instruction input again by the user is received in the process of playing the read-in voice of the wake-up word, and plays back the read-in voice. Therefore, the user can quickly learn the voice from the beginning again, and the time wasted by waiting for the voice to be played is avoided.

When N > 1, the display device 200 may be configured to: in the process of playing the read-in voice of the wake-up word once, if a read-in command input by the user again is received, the display device 200 stops playing the read-in voice and replays the read-in voice once. Therefore, the user can not only quickly learn the read-in voice from the beginning, avoid the time wasted by waiting for the completion of the playing of the voice, but also avoid increasing the playing times of the read-in voice, so as to avoid excessively prolonging the time required by the completion of the playing of the read-in voice waiting by the user.

When N > 1, the display device 200 may be configured to: in the process of playing the read-in voice of the wake-up word once, if a read-in command input by the user again is received, the display device 200 stops playing the read-in voice and replays the read-in voice N times. Therefore, the user can not only quickly learn the read-back voice from the beginning, but also increase the learning times of the user so as to provide more learning opportunities for the user.

The display device 200 is configured with a switching process of the voice control mode.

The display device 200 may characterize the degree of similarity between the user's pronunciation of the wake word and the standard pronunciation by the wake value. The range of wake values may be 0-1, wherein the higher the wake value, the higher the degree of similarity between the user's pronunciation of the wake word and the standard pronunciation, i.e., the more standard the user's pronunciation of the wake word. If the wake value is lower, the degree of similarity between the pronunciation of the wake word by the user and the standard pronunciation is lower, i.e. the pronunciation of the wake word by the user is less standard. The display device 200 may be preconfigured with a calculation method and a calculation model of the wake-up value, and when the display device 200 collects the pronunciation of the wake-up word by the user, the corresponding wake-up value may be obtained based on the preconfigured calculation method and calculation model.

The display device 200 is configured with a threshold of wake up values for determining whether the received speech contains wake up words. Wherein, if the wake-up value of the voice received by the display device 200 is greater than or equal to the threshold value of the wake-up value, it is determined that the voice contains a wake-up word. If the wake-up value of the voice received by the display apparatus 200 is less than the threshold of the wake-up value, it is determined that the voice does not contain a wake-up word. When the display device 200 determines that the received voice includes a wake-up word, the far-field voice control function is turned on in response to the wake-up word. Based on the above-mentioned determination process, the higher the threshold value of the wake-up value, the lower the probability that the display device 200 determines that the received speech includes the wake-up word, and accordingly, the user needs to make a more standard pronunciation of the wake-up word, so as to improve the determination probability of the display device 200 for the wake-up word. The lower the threshold value of the wake-up value, the higher the probability that the display device 200 determines that the received speech includes a wake-up word, and correspondingly, the lower the standard requirement for the pronunciation of the wake-up word by the user.

The voice control mode of the display apparatus 200 includes: control mode and read-through mode. The display device 200 may be configured to default to a control mode. At this time, the display apparatus 200 turns on the far-field voice control function in response to the voice of the wake-up word input by the user. In the control mode, if a voice command input by a user is received, the display apparatus 200 will perform a corresponding task in response to the voice command. In order to ensure the effectiveness of the display apparatus 200 to turn on the far-field voice control function, to avoid affecting the normal use of the display apparatus 200 by a user, in the control mode, the display apparatus 200 sets a threshold value of a higher wake-up value, such as the first threshold value. Through the threshold value of the higher awakening value, voices containing awakening words with nonstandard pronunciation can be effectively filtered out, so that the probability of starting the far-field voice control function by mistake is reduced.

However, in the read-in mode, since the user is in the learning process of the pronunciation of the wake word, the non-standard pronunciation of the wake word by the user needs to be permitted, the display device 200 needs to increase the probability of collecting the pronunciation of the wake word by the user as much as possible, so as to evaluate the pronunciation of the user with different standard degrees, and needs to reduce the probability of filtering the pronunciation of the wake word by the user. Thus, in the read-in mode, the display device 200 may be configured to turn down the threshold of the wake-up value, e.g., to a second threshold that is lower than the first threshold, thereby reducing the recognition requirements for the wake-up word to recognize the user's pronunciation of lower standard as the pronunciation of the read-following wake-up word, thereby evaluating the user's pronunciation.

Based on the above procedure, the display apparatus 200 switches the voice control mode from the control mode to the read-in mode and adjusts the threshold of the wake-up value from the first threshold to the second threshold in the process of playing the read-in voice of the wake-up word. In the control mode, when the wake-up value of the voice input by the user is greater than or equal to a first threshold value, the wake-up word input by the user can be identified as a voice command so as to start a far-field voice control function; when the wake-up value of the voice input by the user is smaller than the first threshold value, discarding wake-up words input by the user, and not starting the far-field voice control function. In the collar-read mode, when the wake-up value of the voice input by the user is greater than or equal to a second threshold value, the wake-up word input by the user can be identified as the learning voice so as to start the evaluation process of the learning voice; when the wake-up value of the voice input by the user is smaller than the second threshold value, discarding the wake-up word input by the user, and not starting the evaluation process of the learning voice.

In the control mode, the threshold for the wake-up value may be set to 0.87. The threshold may be determined after meeting test criteria by acoustic testing, including multi-scenario, multi-angle, and multi-distance testing. When the wake value of the user's pronunciation of the wake word is below 0.87, the display device 200 is not awakened. In the collar-read mode, the threshold is adjusted down to 0.3. On the one hand, the pronunciation of the wake-up word can be fully recognized, and on the other hand, the user can be prompted to make no sound and some situations of false wake-up. In the two aspects, besides the main line function of giving the confidence of the wake-up word of the normal pronunciation of the user, accidents such as un-pronunciation and the like are filtered out as much as possible.

The display device 200 is configured with a management process for the audio source channels.

The display device 200 may include a plurality of sound source channels, which may include a channel that plays the read-in voice and a channel that does not play the read-in voice. The display device 200 is configured to close a channel of the non-play read-out voice in response to the read-out instruction, and open the channel of the play read-out voice to mute the channel of the non-play read-out voice, so as to avoid affecting the play effect of the read-out voice.

After the display device 200 starts the channel for playing the collar-read voice, the collar-read voice is played through the channel for playing the collar-read voice, and the channel for playing the collar-read voice is also used for playing the prompt tone of the wake-up word. The display device 200 configures priorities for the two sound sources played by the channel playing the read-in voice, specifically: the playing priority of the prompt tone of the wake-up word is higher than that of the read-in voice.

The display device 200 may be configured to play the read-in voice of the wake-up word N times in succession, N being a positive integer greater than 0. In the process of continuously playing the N-time wake-up word read-up voices through the channel for playing the read-up voices, if learning voices input by a user are received and the learning voices are recognized to contain the wake-up words, the display device 200 stops playing the read-up voices of the wake-up words, and plays prompt tones indicating that the wake-up words are recognized through the channel for playing the read-up voices. Therefore, the user can be prompted by the played prompt voice to recognize the input learning voice, and the evaluation process of the learning result can be quickly entered, so that the evaluation result can be displayed for the user as soon as possible.

If the display device 200 does not recognize that the received voice contains the wake-up word, continuing to play the read-in voice of the wake-up word to prompt that the voice input by the user is invalid.

The display device 200 also displays the read-in prompt of the wake-up word in the form of a guidance page, and the evaluation result display area.

The collar-read prompt is used to prompt the user for a text version of the content that needs to be followed, such as Say "Hey VIDAA".

The evaluation result display area is used for displaying the standard degree of the wake-up word read by the user, namely the similarity between the learning voice input by the user and the collar-read voice, so that the user can learn the learning effect of the user.

The display device 200 may display the read-out prompt and the evaluation result display area in the form of a popup window.

In some embodiments, if the display device 200 displays the guidance page in the form of a popup window, the display device 200 may display the guidance prompt and the evaluation result display area along the popup window, that is, update the content of the guidance page in the popup window to the guidance prompt and the evaluation result display area. Taking the example of the guide page as shown in fig. 6, the display device 200 updates the content in the popup window 602 in response to the read instruction of the user, and displays the updated popup window 602 as the popup window 602 shown in fig. 10, where the updated popup window 602 includes the read prompt Say "Hey VIDAA" and the evaluation result display area 1001.

In some embodiments, if the display device 200 displays a guidance page in the form of a menu page, the display device 200 may display a read-in prompt and an evaluation result presentation area in the form of a pop-up window on the page. Taking the guide page as shown in (3) of fig. 7 as an example, the display device 200 displays a popup window 1101 on the guide page in response to a read instruction of the user, as shown in fig. 11, the popup window 1101 including a read prompt Say "Hey VIDAA", and an evaluation result display area 1102.

S503, when learning voice input by a user is received, comparing the learning voice with the collar-read voice to obtain an evaluation result of the user reading wake-up words.

The user follows the wake-up word based on the prompt information on the guide page and the received collar-read voice to input the learning voice to the display device 200. The display device 200 compares the learning voice with the collar-read voice, and evaluates the learning effect of the user reading the wake-up word to obtain an evaluation result.

The display device 200 may calculate the evaluation result according to the flow shown in fig. 12, and the specific steps are as follows:

s1201, converting the learning voice into a corresponding wake-up value according to a preset algorithm.

The display device 200 may convert the learning speech into a corresponding wake-up value according to a pre-configured wake-up value calculation method and calculation model.

S1202, determining an evaluation result corresponding to the converted wake-up value according to the corresponding relation between the wake-up value and the evaluation result.

The wake-up value and the evaluation result have a corresponding relation, and the corresponding relation can be a pre-stored point-to-point corresponding relation or a corresponding relation obtained through mathematical relation calculation. In order to facilitate the user to accept the evaluation result, normalization processing is carried out, and the evaluation result is displayed in a percentile form. And aiming at the wake-up value interval 0-0.29 of the wake-up word, the non-sounding or sounding content is not processed, and at the moment, the evaluation result is not displayed to the user, or prompt information such as invalid sounding is displayed, so that the user is prompted to continue learning and re-follow. For the wake-up value interval 0.3-0.86 of the wake-up word (the value is represented by x), the score displayed to the user is interval 1-59 (the score is represented by y), the linear fitting formula y=x58/0.56-30 is adopted, and the evaluation result corresponding to the wake-up value in the wake-up value interval is calculated. For the wake-up value interval 0.87-0.99 of the wake-up word (the value is expressed by x), the score displayed to the user is the interval 60-100 (the score is expressed by y), the linear fitting formula y=x40/0.12-230 is adopted, and the evaluation result corresponding to the wake-up value in the wake-up value interval is calculated. Reference may be made to the transition diagram of wake-up values and evaluation results shown in fig. 13, where the abscissa represents the score corresponding to the evaluation result and the ordinate represents the value of the wake-up value. The transition diagram does not include the wake-up value interval 0-0.29, and only illustrates the wake-up value interval 0.3-0.99, wherein the AB segment corresponds to the wake-up value interval 0.3-0.86, and the BC segment corresponds to the wake-up value interval 0.87-0.99.

S504, displaying the evaluation result in the evaluation result display area.

After the evaluation result is calculated, the display device 200 displays the corresponding evaluation result in the evaluation result display area of the guide page. Therefore, the user can learn the pronunciation of the wake-up word at any time, can clearly learn the learning effect of the user, and further can conveniently judge whether the user needs to learn continuously or not so as to achieve a better learning effect, be more convenient for the subsequent use, can accurately pronounce and input the wake-up word, and improve the wake-up probability of the display device 200.

In some embodiments, if the display apparatus 200 displays the guidance page in the form of a popup window and displays the evaluation result display area within the popup window, the display apparatus 200 updates and displays the corresponding evaluation result in the evaluation result display area within the popup window. Taking the evaluation result display area 1001 as shown in fig. 10 as an example, if the display apparatus 200 calculates that the evaluation result is 80, the 80 may be displayed in the evaluation result display area 1001 as shown in fig. 14. An icon for indicating the degree of merit of the evaluation result may also be displayed in the evaluation result display area 1001, as an identification 1401 indicating that learning is good as shown in fig. 14.

In some embodiments, if the display device 200 displays the guide page in the form of a page and the evaluation result display area in the form of a popup window within the page, the display device 200 updates and displays the corresponding evaluation result in the evaluation result display area within the popup window. Taking the evaluation result display area 1101 as shown in fig. 11 as an example, if the display device 200 calculates the evaluation result as 80, the 80 may be displayed in the evaluation result display area 1101 as shown in fig. 15. An icon for indicating the degree of merit of the evaluation result may also be displayed in the evaluation result display area 1101, as an identification 1501 indicating that learning is good shown in fig. 15.

The display device 200 may close the display of the popup window according to the judging procedure shown in fig. 16, and the specific procedure is as follows:

the display apparatus 200 adjusts the voice control mode from the control mode to the read-in mode, and after the threshold of the wake-up value is adjusted down from the first threshold to the second threshold, detects whether the user inputs the voice of the wake-up word. And if the voice of the wake-up word input by the user is not detected within the appointed time, such as 15 seconds, after the playing of the read-in voice of the wake-up word is finished, closing a popup window for displaying the read-in prompt and the evaluation result display area. If the voice of the wake-up word input by the user is detected, the learning voice is evaluated.

The display device 200 displays the evaluation result in the popup window, and if the display duration is equal to the duration threshold, for example, 3 seconds, the popup window is closed. The display device 200 will adjust the voice control mode from the read-in mode to the control mode and up-adjust the threshold of the wake-up value from the second threshold to the first threshold to resume the standard detection process of the wake-up word.

The display device responds to the collar reading starting operation of the user, and displays a guide page of the wake-up word, wherein the guide page comprises a collar reading button of the wake-up word. The display device responds to a collar reading instruction input by a user based on the collar reading button, plays collar reading voice of the wake-up word, displays a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluates a result display area. When receiving learning voice input by a user, the display device compares the learning voice with the collar-read voice to obtain an evaluation result of the user reading wake-up words, and displays the evaluation result in an evaluation result display area. The user can start the collar-read mode at any time to learn the pronunciation of the wake-up word, and can master the accuracy of the user to the pronunciation of the wake-up word based on the evaluation result.

The foregoing description, for purposes of explanation, has been presented in conjunction with specific embodiments. However, the above discussion in some examples is not intended to be exhaustive or to limit the embodiments to the precise forms disclosed above. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the disclosure and to enable others skilled in the art to best utilize the embodiments.

Claims (10)

1. A display device, characterized by comprising:

a controller configured to:

responding to a starting instruction of a user, and controlling a display to display a guide page of a wake-up word, wherein the guide page comprises a read-out button of the wake-up word;

responding to a collar reading instruction input by a user based on the collar reading button, playing collar reading voice of the wake-up word, controlling the display to display a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluating a result display area;

when learning voice input by a user is received, comparing the learning voice with the collar-read voice to obtain an evaluation result of the wake-up word read by the user;

and controlling the display to display the evaluation result in the evaluation result display area.

2. The display device of claim 1, wherein the controller, in response to a collar read initiation operation by the user, prior to controlling the display to display a guide page of the wake-up word, is configured to:

and if the starting instruction is an instruction input by a user for starting a microphone switch, responding to the starting instruction, controlling the display to display the guide page in a popup window mode, and displaying the read-in button in the popup window.

3. The display device of claim 1, wherein the controller, in response to a user initiation instruction, controls the display to display a guide page of a wake-up word configured to:

and if the starting instruction is an instruction input by a user selecting a hands-free mode option in a voice assistant menu, controlling the display to display the guide page in response to the starting instruction, wherein the guide page comprises content related to the wake-up word and the read-out button.

4. A display device according to any one of claims 1 to 3, wherein the controller, in response to a read instruction input by a user based on the read button, plays a read voice of the wake-up word and controls the display to display a read prompt of the wake-up word in a popup window form within the guide page, and the evaluation result presentation area is configured to:

switching a voice control mode from a control mode to a read-in mode, closing a channel for not playing the read-in voice, and adjusting a threshold value for judging a wake-up value of the wake-up word from a first threshold value to a second threshold value, wherein the wake-up value is used for representing the similarity degree of the received voice and the standard pronunciation of the wake-up word, and the lower the threshold value of the wake-up value is, the easier the received voice is judged as the wake-up word;

And in the read-in mode, the controller recognizes the wake-up word input by the user as learning voice, the control mode corresponds to the first threshold value, the read-in mode corresponds to the second threshold value, and the second threshold value is lower than the first threshold value.

5. A display device according to any one of claims 1 to 3, wherein the controller, in response to a read instruction input by a user based on the read button, plays a read voice of the wake-up word and controls the display to display a read prompt of the wake-up word in a popup window form within the guide page, and the evaluation result presentation area is configured to:

detecting whether a focus is positioned on the collar reading button or not when the collar reading voice of the wake-up word is played;

and stopping playing the collar-reading voice of the wake-up word if the focus is detected to leave the collar-reading button.

6. A display device according to any one of claims 1 to 3, wherein the controller, in response to a read instruction input by a user based on the read button, plays a read voice of the wake-up word and controls the display to display a read prompt of the wake-up word in a popup window form within the guide page, and the evaluation result presentation area is configured to:

If receiving a read command input by the user based on the read button again when playing the read voice of the wake-up word, responding to the read command input again, and playing the read voice of the wake-up word again.

7. A display device according to any one of claims 1 to 3, wherein the controller continuously plays the read-in voice of the wake-up word N times, N being a positive integer greater than 0, the controller, in response to a read-in instruction input by a user based on the read-in button, plays the read-in voice of the wake-up word and controls the display to display the read-in prompt of the wake-up word in a popup window form in the guide page, and the evaluation result display area is configured to:

if the learning voice is received in the process of playing the N times of the leading voice of the wake-up word, and the learning voice is recognized to contain the wake-up word, stopping playing the leading voice of the wake-up word, and playing a prompt tone indicating that the wake-up word is recognized.

8. The display device of claim 4, wherein the controller, upon receiving a learning voice input by a user, compares the learning voice with the collar-read voice to obtain an evaluation result of the wake-up word followed by the user, is configured to:

Converting the learning voice into a corresponding wake-up value according to a preset algorithm;

and determining the evaluation result corresponding to the converted wake-up value according to the corresponding relation between the wake-up value and the evaluation result.

9. A display device according to any one of claims 1-3, wherein the controller controls the display to display the evaluation result in the evaluation result presentation area, and is further configured to:

when the display duration of the evaluation result is equal to a duration threshold, closing the popup window, switching the voice control mode from the read-in mode to the control mode, opening a channel for not playing the read-in voice, and adjusting a threshold for judging the wake-up value of the wake-up word from the second threshold to the first threshold.

10. A method for reading wake-up words, characterized by being applied to a display device according to any one of claims 1-9;

the method comprises the following steps:

responding to a starting instruction of a user, displaying a guide page of a wake-up word, wherein the guide page comprises a read-out button of the wake-up word;

responding to a collar reading instruction input by a user based on the collar reading button, playing collar reading voice of the wake-up word, displaying a collar reading prompt of the wake-up word in a popup window mode in the guide page, and evaluating a result display area;

When learning voice input by a user is received, comparing the learning voice with the collar-read voice to obtain an evaluation result of the wake-up word read by the user;

and displaying the evaluation result in an evaluation result display area.