JP2020190836A - Video signal processing apparatus and video signal processing method - Google Patents

Abstract

To provide a video signal processing apparatus which can implement control easier to use than conventional one by combining a voice control technique with a parental control function in accordance with one embodiment.SOLUTION: The video signal processing apparatus of one embodiment comprises: a voice signal input unit which receives a voice instruction; a speaker specification unit which specifies a speaker who is a source of the voice instruction received by the voice signal input unit, and his or her age; a determination unit which determines whether or not the voice instruction is acceptable for preliminarily set restriction information on the basis of the specified age and the voice instruction; a control execution unit which executes the voice instruction when the determination unit determines that the voice instruction is acceptable; and a warning output unit which outputs warning when the determination unit determines that the voice instruction should be rejected.SELECTED DRAWING: Figure 1

Description

The present embodiment relates to a video signal processing device and a video signal processing method.

In recent years, with the improvement of voice recognition technology, the number of devices capable of controlling by voice is increasing. Video signal processing equipment is no exception. For example, a user can control the power on / off and channel change by simply uttering a voice such as "turn on the power" or "change channel" without operating the remote controller. It has become.

On the other hand, the video signal processing device has a parental control (viewing restriction) function, and a restricted age is given as program information to program contents having extreme contents. By using the program information, it is possible to restrict viewing of the content to children who do not reach the permissible age.

Japanese Unexamined Patent Publication No. 2005-223846

The mechanism of parrent control in the conventional video signal processing device is mainly to set the age information that can be viewed without limitation in the video signal processing device in advance, and if the age information of the program is set in the video signal processing device. If the age range is out of the range, the program cannot be viewed until the unlock code is entered.

For example, if the video signal processing device is set to have a parrent control age of 14 years or older, content with a target age of 14 years or younger can be viewed without limitation regardless of the viewer's age. When viewing content with information that the age is 19, even if the viewer is 20 years old or older, the parrent lock must be released in order to view it regardless of that age. Must be.

As described above, on the video signal processing device, it is necessary for a person who is actually allowed to watch the program to enter a release code when the viewer cannot watch the program due to the restrictions attached to the program. Also, in the parrent lock method of the above example, if a child whose viewing should be restricted knows, even the child can freely release the restriction on the program and watch it until the release code is changed. There was a problem.

Therefore, in this embodiment, by combining the parental control function with the voice control technology, it is an object to provide a video signal processing device and a video signal processing method that are easier to use than before and the parental lock function is also reliable. To do.

In another embodiment, when executing a process based on a voice command, the command input person is specified in advance, the restriction / release of the parrent control is performed from the age information of the command input person, and the operation input of the release code is performed. It is an object of the present invention to provide a video signal processing device video signal processing method capable of performing without requiring.

According to the video signal processing device of one embodiment
A voice signal input section where voice commands are input, and
A speaker that is the source of the voice command input from the voice signal input unit, a speaker identification unit that specifies the age of the speaker, and a speaker identification unit.
Based on the specified age and the voice command, a determination unit for determining whether the voice command should be allowed or denied with respect to preset restriction information.
When the determination unit determines that the voice command should be allowed, the control execution unit that executes the voice command and the control execution unit
A warning output unit that outputs a warning when the determination unit determines that the voice command should be denied can be provided.

Further, in a system for inputting the voice command to the determination unit, a voice recognition unit for converting voice data in the voice band into text and a natural language understanding unit for converting text data into machine language (mechanical command) are used.

FIG. 1 is a configuration explanatory view showing an overall configuration of a video signal processing device according to an embodiment of the present invention. FIG. 2 is a partial configuration diagram showing a block that functions when user information is preset in the video signal processing device shown in FIG. FIG. 3 is an explanatory diagram of the video signal processing device shown in FIG. 1 when a user who is not subject to parrent restrictions selects a channel. FIG. 4 is an explanatory diagram of the video signal processing device shown in FIG. 1 when a user subject to parrent restrictions selects a channel. FIG. 5 is a flowchart illustrating an operation example of the video signal processing device shown in FIG. FIG. 6 is a flowchart illustrating another operation example of the video signal processing device shown in FIG.

Hereinafter, embodiments will be described with reference to the drawings. FIG. 1 is an embodiment, for example, an example applied to a broadcast receiving device 100. The basic configuration 50 of the receiving system in the broadcast receiving device 100 includes a tuner device 51, a video / audio data processing device 53, a video signal output unit 54, an audio signal output unit 55, a recording / playback medium connection unit 56, and the like. Furthermore, a network connection 52 is also provided so that communication with an external server or the like can be performed. For example, the external server has a video distribution function by video on demand, and the viewer can also view the distributed image. Furthermore, it is also possible to upload the viewing log to an external server. The external server can analyze viewing logs from a large number of broadcast receiving devices and provide information such as recommended programs and commercial commercials that are currently popular to viewers.

Here, the video signal processing device of the present embodiment includes a microphone (audio signal input unit) 11. The data acquired by the microphone 11 is input to the voice recognition unit 12 and the feature amount detection unit 14. The voice recognition unit 12 converts the voice data in the voice band into text and inputs the text data to the natural language understanding unit 13 which converts the text data into a machine language (mechanical instruction). That is, the voice recognition unit 12 and the natural language understanding unit 13 understand (decode) the utterance content by voice using dictionary data or the like, output a command, and input the command to the parrent control determination unit 17. The voice recognition unit 12 and / or the natural language understanding unit 13 may be provided on an external server via the Internet. The command based on the utterance content understood by the natural language understanding unit 13 is sent to the parrent control unit 17.

On the other hand, the feature amount detection unit 14 analyzes, for example, the voiceprint of the speaker and outputs the voiceprint analysis data. The voiceprint analysis data is input to the speaker identification unit 15. The voiceprint analysis data (feature amount) of the individual speaker is registered in the database 16 in advance. In the example of the figure, user A (age 43),
The feature amounts of user B (age 41), user C (age 15), and user D (age 10) are registered in the database 16, respectively.

The speaker identification unit 15 compares the input new voiceprint analysis data with the plurality of registered voiceprint analysis data registered in the database 16 one after another, and identifies the speaker corresponding to the new voiceprint analysis data.

The age of the identified speaker is also registered in the database. This reveals how old the speaker (user) who is currently speaking is.

The parrent control determination unit 17 receives the identified speaker, its age, and program information of the program to be parrented and controlled (locked).

The age limit is specified in the program information for programs that should be controlled (locked). That is, the program information is stored in the database 18 with a channel and a mark (identification data) to be restricted. The database 18 stores a pair of data on the age limit to be restricted and the channel to be restricted. In the example of this figure, the Ych channel is restricted to 12 years or younger, and the Zch channel is restricted to 18 years or younger. The program information may include the program information of the program recorded in the video reproduction device 22.

The parrent control determination unit 17 receives information on the specified speaker, its age, and the program to be parrented and controlled (locked), and determines as follows.

That is, it is assumed that the new speaker is user D and utters, for example, "make it a Ych channel". At this time, the user D is 12 years old or younger, while the Ych channel is restricted to 12 years old or younger. Therefore, the parrent control determination unit 17 determines that the channel cannot be switched, and the determination result is obtained. Is notified to the control execution unit 21. Then, the control execution unit 21 outputs a warning by the warning output unit (display and / or voice) 23, for example, "This program cannot be viewed". Further, an output (or reproduction) stop signal is output to the recording / reproducing device 23.

The operation order of each block is controlled based on the control of the system control unit 30.

As described above, in this system, it is possible to identify an individual by voiceprints or the like. For this reason, "release" and "restriction" are surely performed for each individual and each receiving device for the program under pan rental control.

FIG. 2 shows a configuration for, for example, home users A, B, C, and D to construct voice features and age information in a management table. The parts common to FIG. 1 will be described with the same reference numerals as those in FIG.

The user switches the device to the user registration mode by operating, for example, a remote controller (not shown) or a specific operation key provided on the broadcast receiving device 100. In this case, the input by the operation key is preferably a specific personal identification number known only to the father (for example, user A) or the mother (for example, user B) who manages the broadcast receiving device 100, for example. When the device enters the registration mode, the speaker age information setting unit 51 is activated, and the speaker (for example, user C or D) to be registered is set to the voice input mode.

In this case, it is preferable that the administrator (for example, user A) first registers the feature amount of the voice as the administrator in advance. After that, when registering the voice features of future registrants (for example, user C or D) excluding the administrator (for example, user A), the administrator gives an instruction to the future registrants by voice. This is because it may be issued. In such a registration mode, even if the administrator's voice is detected, the speaker identification unit 15 ignores the administrator's voice and recognizes the newly detected feature amount of the speaker as a new user. And register it in the database 16. Then, it waits for the input of the age information of the user.

The age information is detected by the speaker age information setting unit 51 and registered in the database 17. The age information can be input by a remote controller or voice input, for example. In the case of voice input, the age at which the user with the previously detected voiceprint speaks is detected. For example, the age is judged by understanding the utterances such as 10 years old or 6 years old. As a result, the user, the age of the user, and the voice feature amount data of the user are registered in the database 16 in association with each other.

Regarding the above registration, the display of the operation guide such as the operation guide voice and / or the character is output based on the sequence control of the system control unit 30.

FIG. 3 shows an example in which user C (15 years old) instructed channel Xch by utterance as channel switching by voice, for example. For example, an example of uttering "Set the channel to Xch" is shown. This utterance is converted into text by the voice recognition unit 12, converted into a command word (for example, Chang ch: X) by the natural language understanding unit 13, and input to the parrent control determination unit 17. In this case, the speaker is identified as 15 years old on the database 16, and the natural language understanding unit 13 detects that the speaker has instructed to switch to the Xch channel.

The parrent control determination unit 17 refers to the database 18 and determines whether or not the Xch channel is restricted based on the program information. Since there is no viewing restriction on the Xch channel on the database 18, the parrent control determination unit 17 instructs the control execution unit 21 to switch to the Xch channel. In the same operation, switching to the Xch channel is executed even if the user D instructs the Xch channel.

FIG. 4 shows an example in which user D (10 years old) instructed the Zch channel by utterance as channel switching by voice, for example. In this case, the speaker is identified as 10 years old on the database 16, and the natural language understanding unit 13 detects that the speaker has instructed to switch to the Zch channel.

The parrent control determination unit 17 refers to the database 18 and determines whether or not the Zch channel is restricted based on the program information. On database 18,
There are restrictions on people under the age of 18. Therefore, the parrent control determination unit 17 notifies the control execution unit 21 to refuse the switching of the Zch channel. Then, in this case, the warning output unit 23 outputs a warning such as "This program cannot be viewed". In FIGS. 3 and 4, the same parts as those in FIG. 1 are designated by the same reference numerals, and the description thereof will be omitted.

Various methods can be used as the type of program viewing restriction processing executed by the control execution unit 21. For example, the channel reception itself of the restricted program is restricted, or the channel is received but the program is not demodulated, or the program is demodulated but the output is stopped, and all the outputs are black level or white level. Various methods are possible, such as making an image of.

The system is not limited to the above embodiments. The device operation function and the speaker identification function by voice commands do not need to be provided in the broadcast receiving device 100, and may be provided in an external device through a network. Therefore, in the broadcast receiving device 100, for example, a microphone 11, a parrent control determination unit 17, a control execution unit 21, a warning output unit 23, a system control unit 30, and a basic configuration 50 are provided, and a voice recognition unit 12 and a natural language recognition unit 12 are provided. The language understanding unit 13, the feature amount detection unit 14, the speaker identification unit 15, the databases 16 and 18, and the like may be provided externally. Further, the parrent control determination unit 17 may be provided outside.

The speaker identification unit 15 memorizes (learns) the voice of the user who operates the device in advance, and determines that the person is the same person based on the degree of similarity with the voice. However, it is also possible to estimate the age group of the voice by using the feature amount (frequency component, etc.) of the voice command data without pre-learning the user voice. In this case, although it is difficult to estimate the exact age, it is possible to realize control that the viewing restriction is applied to the obvious child voice, while the viewing restriction is not applied to the obvious adult voice.

The age information of the speaker was set in advance. Furthermore, by inputting the date of birth, a function to automatically adjust the age information (when the birthday comes) may be added. As the viewing content, programs provided by broadcasting stations such as terrestrial digital broadcasting and BS are assumed, but even if it is network streaming content such as YouTube (registered trademark) or Netflix (registered trademark), information on the age limit can be used. It can be applied to all content that you have.

Actually, when the voice command of "Set channel ..." is caught in the viewing restriction, the channel is not changed, the channel is changed but the screen is black, and the first available channel after the specified channel It is also possible to add functions such as making a change to, telling by voice that the channel change has failed, and displaying on the screen that the channel change has failed.

As described above, since this system can perform voice recognition and age recognition of the user, it is also possible to obtain the following operations.

FIG. 5 shows a case where, for example, a child (10 years old) utters "Switch to Ych channel". In this case, in this system, the Ych channel rejects viewing and issues a warning to a 10-year-old child (steps As1, As2). However, if the father is in the same room and decides that "the current program of Ych can be watched by the child", the father utters "switch to the Ych channel" and switches to the Ych channel. Can be realized (steps As3, As4).

FIG. 6 shows another operation example. Suppose that his father (43 years old) is watching a program on the Ych channel (step Bs1). Here, for example, it is assumed that a child (10 years old) enters the room and the system of the present embodiment recognizes the voice of the child (step Bs2). The voice at this time is not limited to the voice command to the broadcast receiving device 100.

Then, the system automatically switches to the Xch channel (program without restrictions) (step Bs31), outputs a warning telop or sound (step Bs32), or hides the image (entire surface). Any process such as switching to black or white) (step Bs33) is executed. Then, it waits for the next operation (step Bs34), and ends the process if there is the next operation. It is possible for the user (administrator) to select and set in advance which of steps Bs31, Bs32, and Bs33 is to be executed. Alternatively, either of them may be set at the time of shipment of the broadcast receiving device 100.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The modifications of these embodiments are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof. Furthermore, in each of the constituent elements of the claims, even when the constituent elements are divided and expressed, when a plurality of the constituent elements are expressed together, or when these components are expressed in combination, it is within the scope of the present invention. Further, a plurality of embodiments may be combined, and examples composed of these combinations are also within the scope of the invention.

Further, the apparatus of the present invention is applied even when the claim is expressed as a control logic, when it is expressed as a program including an instruction for executing a computer, and when it is expressed as a computer-readable recording medium in which the instruction is described. is there. Further, the names and terms used are not limited, and other expressions are included in the present invention as long as they have substantially the same contents and the same purpose.

11 ... Microphone, 12 ... Voice recognition unit, 13 ... Natural language understanding unit, 14 ... Feature detection unit, 15 ... Speaker identification unit, 17 ... Parent control judgment unit , 21 ... Control execution unit, 20 ... Basic configuration, 100 ... Broadcast receiver.

Claims (7)

A voice signal input section where voice commands are input, and
A speaker that is the source of the voice command input from the voice signal input unit, a speaker identification unit that specifies the age of the speaker, and a speaker identification unit.
Based on the specified age and the voice command, a determination unit for determining whether the voice command should be allowed or denied with respect to preset restriction information.
When the determination unit determines that the voice command should be allowed, the control execution unit that executes the voice command and the control execution unit
A warning output unit that outputs a warning when the judgment unit determines that the voice command should be denied.
Video signal processing device equipped with. The video signal processing device according to claim 1, wherein the voice command is input to the determination unit after the language is recognized by the language understanding unit. The execution in response to the voice command
The video signal processing device according to claim 1, which is either a display process or a reception process of a program of a broadcast channel or a playback process from a recording / playback device. The video signal processing device according to claim 2 or 3, wherein at least one of the speaker identification unit, the determination unit, and the language understanding unit is arranged outside via a network. Input a voice command to the voice signal input section,
The speaker identification unit identifies the speaker who is the source of the voice command input from the voice signal input unit and the age of the speaker.
The language comprehension department recognizes the language of the voice command and
Based on the specified age, the voice command, and the recognized language, the determination unit should allow or deny the voice command for preset restriction information. Judging,
When the control execution unit determines that the voice command should be allowed, the judgment unit executes the voice command.
A video signal processing method that outputs a warning when the judgment unit determines that the audio command should be denied by the warning output unit. Even when the warning is output by the warning output unit, if a second voice command from a different speaker is input as the voice command, the determination unit determines that the second voice command is allowed. The video signal processing method according to claim 5. When the voice command is executed by the control execution unit and the judgment unit determines from the age related to the newly input voice signal that the current execution should be denied, a warning or a channel The video signal processing method according to claim 5, wherein the switching is determined.

Images