Notification device, notification method, notification program and recording medium
Patent Information
- Application Number
- JP2024229042
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-12-25
- Publication Date
- 2025-03-14
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 2025036566000001_ABST
Abstract
Description
[Technical field]
[0001] The present application relates to a method for notifying a user when a specific word is spoken. [Background technology]
[0002] For example, Patent Document 1 discloses an alarm device that notifies a user when the user uses voice data that the user wants to be notified of. Specifically, comparison source voice data such as "...or maybe..." or "Oops" is input and stored in this alarm device. The alarm device then issues an alarm when the user's voice signal input by a microphone matches the comparison source voice data. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2006-349843 A Summary of the Invention [Problem to be solved by the invention]
[0004] There are devices that recognize commands from a user through voice recognition and operate based on those commands. It is not appropriate to issue a notification just because the words uttered as commands to such devices match specific words. Also, if a notification is issued simply because the uttered words happen to match specific words, there is a possibility that excessive notifications will be issued. On the other hand, inappropriate words can sometimes become catchphrases without people realizing it. It is hoped that pointing out such catchphrases will provide an opportunity to correct inappropriate catchphrases.
[0005] The present invention has been made in consideration of the above points, and one example of an object of the present invention is to provide an alarm device, an alarm method, an alarm program, and a recording medium that make it possible to make a speaker aware of inappropriate catchphrases, excluding words for controlling a specific device. [Means for solving the problem]
[0006] In order to solve the above problem, the invention described in claim 1 is an alarm device comprising: an acquisition means for acquiring controlled word information indicating words used in controlling a specified device and non-controlled word information indicating words not used in controlling the specified device based on voice input using a sound input means; a memory control means for storing the acquired non-controlled word information in a memory means; an identification means for identifying a word that has been used more than a specified number of times based on the stored non-controlled word information; and an alarm control means for alarming information indicating the identified word when the identified word corresponds to a word predetermined as an inappropriate word. [Brief description of the drawings]
[0007] [Figure 1] 1 is a block diagram showing an example of a schematic configuration of an alarm device according to an embodiment; [Diagram 2] 1A is a diagram illustrating an example of a vehicle according to an embodiment, and FIG. 1B is a block diagram illustrating an example of a navigation device according to an embodiment. [Diagram 3] 1A is a diagram illustrating an example of information stored in an inappropriate word database according to an embodiment, and FIG. 1B is a diagram illustrating an example of information stored in an utterance history database according to an embodiment. [Figure 4] FIG. 4 is a diagram showing an example of notification by the navigation device according to the embodiment. [Diagram 5] 5 is a flowchart illustrating an example of a process performed by the navigation device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0008] First, an embodiment of the present application will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of a schematic configuration of a notification device according to an embodiment.
[0009] As shown in FIG. 1, the notification device D according to the embodiment is configured to include an acquisition unit 1, a storage control unit 2, a specification unit 3, and a notification control unit 4.
[0010] In this configuration, the acquisition means 1 acquires control word information indicating words used to control a predetermined device and non-control word information indicating words not used to control the predetermined device, based on a voice input using the sound input means 5. The predetermined device may be the same as the notification device D or may be different.
[0011] The storage control means 2 causes the storage means 6 to store the non-controlled word information acquired by the acquisition means 1 .
[0012] The identifying means 3 identifies words that have been used more than a predetermined number of times based on the non-controlled word information stored in the storage means 6.
[0013] When the word specified by the specifying means 3 corresponds to a word that is predetermined as an inappropriate word, the notification control means 4 causes notification information indicating the specified word to be notified.
[0014] As described above, when an inappropriate word that is not used to control a specific device is spoken more than a certain number of times, the word is notified. Therefore, it is possible to make the speaker aware of an inappropriate catchphrase, excluding a word for controlling a specific device. EXAMPLES
[0015] Next, a specific example corresponding to the above-described embodiment will be described with reference to Figures 2 to 5. The example described below is an example in which the embodiment is applied to a navigation device that can be mounted on a vehicle.
[0016] [1. Configuration of navigation device] FIG. 2(a) is a diagram showing an example of a vehicle according to an embodiment. FIG. 2(b) is a block diagram showing an example of a navigation device according to an embodiment. FIG. 3(a) is a diagram showing an example of information stored in an inappropriate word database according to an embodiment. FIG. 3(b) is a diagram showing an example of information stored in an utterance history database according to an embodiment. FIG. 4 is a diagram showing an example of a notification by the navigation device according to an embodiment. FIG. 5 is a flowchart showing an example of a process by the navigation device according to an embodiment.
[0017] 2, the navigation device 10 according to the embodiment can be mounted on a vehicle 30. The navigation device 10 may mainly perform processing for guiding the vehicle 30 to a destination.
[0018] 2(b), the navigation device 10 includes a control unit 11, a storage unit 12, a communication unit 13, a display 14, a speaker 15, a microphone 16, an input unit 17, and an interface unit 18. The control unit 11 to the interface unit 18 are connected via a bus 19.
[0019] The control unit 11 includes a CPU, a ROM, a RAM, etc. The CPU reads out and executes various programs stored in the ROM or the storage unit 12, causing the control unit 11 to execute various processes described below.
[0020] The storage unit 12 is configured with a non-volatile memory such as a hard disk, a flash memory, etc. The storage unit 12 stores various programs for controlling the navigation device 10. The various programs may be read from a recording medium via a drive device (not shown), for example, or may be downloaded from a predetermined server device via a network.
[0021] Furthermore, road data is stored in the storage unit 12. The road data is data related to roads. For example, the road data may indicate the type, distance, shape, etc. of each road, as well as the connection state between roads and the longitude and latitude of the road connection points.
[0022] Furthermore, the storage unit 12 stores command words indicating words for controlling the operation of the navigation device 10. When an occupant of the vehicle 30 issues one command word or a combination of multiple command words by voice, the navigation device 10 recognizes the command from the occupant through voice recognition and operates according to the command. Examples of the controlled operation of the navigation device 10 include searching for a destination, displaying a map, and route guidance. The command words may be expressed, for example, as text information. For example, the storage unit 12 may store a voice command database, a genre database, a location information database, and the like. These databases include command words. The voice command database stores command words indicating words as commands to the navigation device 10 and information indicating the operation of the navigation device 10 corresponding to the command in association with each other. Examples of command words include "name," "address," "neighborhood," "current location," "view map of destination," "go here," "drop in," "view map," and "erase route." The genre database stores genre information indicating each genre of the facility as a command word. Examples of genres include "convenience store," "gas station," "parking lot," and "family restaurant." In the location information database, name information indicating the name of each location, information indicating the genre of the location, and information indicating the longitude and latitude of the location are stored in association with each other as command words. Note that the navigation device 10 may be capable of playing music, playing videos, receiving television broadcasts, receiving radio broadcasts, etc. A database containing command words for controlling such processes may be stored in the storage unit 12.
[0023] Furthermore, the storage unit 12 stores an inappropriate word database, a speaker database, and an utterance history database. The inappropriate word database stores an inappropriate word dictionary that includes one or more inappropriate words that indicate inappropriate words. The inappropriate word dictionary may be expressed, for example, as text information. The inappropriate words may include, for example, at least one of rude words to the person to whom the words are directed, words that make the person to whom the words are directed uncomfortable, dirty words, words that give a negative impression, slang, discriminatory language, and the like. The inappropriate word database may store a plurality of inappropriate word dictionaries that indicate inappropriate words according to a plurality of different situations in which the speaker is placed. Examples of situations in which the speaker is placed include a case where the speaker speaks as the driver of the vehicle 30, a case where the speaker speaks as a passenger in the vehicle 30 rather than as a driver, a case where a parent (or simply an adult) speaks to a child, and the like. As shown in FIG. 3(a), the inappropriate word database may store inappropriate word dictionaries for the driver, the passenger, and the parent, for example. The words that are inappropriate for the driver to use may include, for example, foul language expressing complaints or dissatisfaction with other vehicles around the vehicle 30, the driver of the vehicle, or pedestrians, or traffic conditions. Examples of such words include "What the heck," "You bastard," "You're in the way," "Tch" (clicking the tongue), sighing, and the like. The words that are inappropriate for the passenger to use may include, for example, words expressing complaints or dissatisfaction with the driving of the driver of the vehicle 30, or words that put a burden on the driver. Examples of such words include "I thought there would be a traffic jam after all," "Are we there yet?", "Will we make it in time?", and the like. The words that are inappropriate for the parent to use may include, for example, slang that the parent would not want their child to remember, or words that strongly scold a child. Examples of such words include "Yabai," "Mekkaku," "Kaku," "No," "Hurry up!", "Wait a minute," "Do it," and the like. The inappropriate word database may store a standard dictionary of inappropriate words that indicate inappropriate words in any situation. Among the inappropriate word dictionaries stored in the inappropriate word database, an inappropriate word dictionary to be used for notifying of an inappropriate catchphrase may be selectable in advance by a passenger of the vehicle 30.For example, one or more profanity dictionaries may be selectable.
[0024] In the inappropriate word database, at least one of a notification information template and a notification mode may be stored in association with each inappropriate word dictionary. The notification information template is a template of notification information that is notified when an inappropriate word uttered by a passenger of the vehicle 30 is a habitual phrase of the passenger. This template may be, for example, text information or a voice feature vector of the notification information. One notification information template may be stored in each inappropriate word dictionary, or one notification information template may be stored for each of one or more inappropriate words of the same type included in the inappropriate word dictionary. In the case of the inappropriate word dictionary for the driver, the template may be, for example, "Calm down a little. XXX is not good." Here, "XXX" is an inappropriate habitual phrase. It is considered that the message of this template has the effect of calming the driver's feelings. In the case of the inappropriate word dictionary for the passenger, the template may be, for example, "XXX may be a bit harsh for the driver." In the case of a word in the parent's inappropriate word dictionary that strongly scolds a child, the template may be, for example, "XXX is a slightly overbearing way of speaking to children." The notification mode indicates by which means the message is to be notified. The notification mode may be, for example, "direct" or "speaker terminal." "Direct" indicates that notification is made directly by the navigation device 10. "Speaker terminal" indicates that notification is made by a terminal device carried by the speaker. Examples of portable terminal devices include mobile information terminals such as smartphones and tablet computers, mobile phones, and PDAs (Personal Digital Assistants). For example, notification information may be sent to the terminal device by short messages, e-mails, etc.
[0025] The speaker database stores information about the speaker. For example, the speaker database may store a voice feature vector for each speaker in association with a speaker ID. The speaker ID is identification information for identifying the speaker. For example, the navigation device 10 may automatically generate the speaker ID. The voice feature vector is a feature vector indicating the characteristics of the voice uttered by the speaker. The speaker database may further store at least one of the speaker's name and the notification information destination information in association with the speaker ID. The notification information destination information is information indicating the destination of the notification information. For example, the notification information destination information may be the caller's telephone number or email address.
[0026] The speech history database stores the history of utterances made by passengers of the vehicle 30. The speech history database may store the history of only inappropriate words among the words uttered. For example, the speech history database may store, for each utterance, a non-command word and the date and time of use in association with a speaker ID. The speaker ID indicates the passenger who made the utterance. The non-command word indicates, among words uttered by the passenger, a word that is not used to control the navigation device 10. The date and time of use indicates the date and time when the word was uttered. The speech history database shown in FIG. 3(b) indicates that speaker A uses "What is it?" twice and "You're in the way" once. Meanwhile, speaker B uses "Are we there yet?" once.
[0027] The communication unit 13 controls communication with other devices via wireless communication. The communication unit 13 may include, for example, a network adapter and an antenna. For example, the communication unit 13 may be connectable to a network such as the Internet via a base station (not shown). Furthermore, for example, the communication unit 13 may be capable of communicating with a portable terminal device.
[0028] The display 14 displays various information under the control of the control unit 11. The display 14 may be, for example, a liquid crystal display or an organic EL display. The speaker 15 outputs various sounds under the control of the control unit 11. The microphone 16 collects sounds such as the speech of an occupant of the vehicle 30 and converts the collected sounds into audio signals. The microphone 16 outputs the audio signals to the control unit 11. The microphone 16 is an example of an audio input means. The input unit 17 is composed of, for example, a touch panel, a button, a switch, etc., and outputs an operation signal indicating the content of an operation by an occupant of the vehicle 30 to the control unit 11.
[0029] The interface unit 18 is connected to the vehicle speed sensor 21, the acceleration sensor 22, the gyro sensor 23, the GNSS sensor 24, and the camera 25. The interface unit 18 performs interface processing between the navigation device 10 and the vehicle speed sensor 21 to the camera 25. Each of the vehicle speed sensor 21 to the camera 25 is mounted or installed on the vehicle 30.
[0030] The vehicle speed sensor 21 detects the traveling speed of the vehicle 30 and outputs speed information indicating the detected speed to the interface unit 18. The acceleration sensor 22 detects the acceleration of the vehicle 30 and outputs acceleration information indicating the detected acceleration to the interface unit 18. The gyro sensor 23 detects the angular velocity of the vehicle 30 and outputs angular velocity information indicating the detected angular velocity to the interface unit 18. The GNSS sensor 24 receives a signal transmitted from a navigation satellite (not shown) using a GNSS (Global Navigation Satellite System), calculates the position of the vehicle 30 based on this signal, and outputs position information (e.g., longitude and latitude) indicating the calculated position to the interface unit 18. The GNSS used may be, for example, a GPS (Global Positioning System) or another system. The camera 25 is composed of, for example, a CCD (Charge Coupled Device) sensor, captures an image inside the vehicle 30, and outputs image data indicating the captured image to the interface unit 18. This image data may be a still image or a video. The interior of the vehicle 30 is a space in which there are seats provided in the vehicle 30. For example, the camera 25 may be installed in the vehicle 30 so that the face of any person sitting in any seat can be photographed.
[0031] [2. Functions of the control unit of the navigation device] [2-1. Voice control] The control unit 11 controls the operation of the navigation device 10 according to the voice uttered by the passenger of the vehicle 30. The passenger inputs a voice from the microphone 16. The control unit 11 generates a voice feature vector, for example, by performing a Fourier transform on the input voice signal. The control unit 11 generates word information indicating the words uttered by the passenger by performing voice recognition based on the generated voice feature vector. When the words uttered by the passenger match an instruction word stored in, for example, a voice command database, a genre database, or a location information database, or match a combination of multiple instruction words stored in these databases, the control unit 11 may execute a process according to the instruction word or combination. For example, the passenger says the word "name" followed by the name of the facility, "ABC." In response to this, the control unit 11 refers to the voice command database and recognizes that a search for a facility by name has been requested. Then, the control unit 11 searches the location information database for facilities with the name "ABC" among facilities within a predetermined distance from the vehicle 30, for example. The control unit 11 displays a list of the searched facilities on the display 14. When the passenger selects any facility from the list, the control unit 11, for example, displays a map of the surroundings of the selected facility on the display 14. Here, when the passenger says "Go here," the control unit 11 refers to the voice command database and recognizes that the selected facility is set as the destination. Then, the control unit 11 searches for a travel route to the destination based on road data. For example, the control unit 11 may periodically calculate the current position of the vehicle 30 using the GNSS sensor 24, obtain position information indicating the current position from the GNSS sensor 24, and store the position information in the storage unit 12. Then, the control unit 11 may update or correct the position information stored in the storage unit 12 based on information output from the vehicle speed sensor 21, the acceleration sensor 22, and the gyro sensor 23. The control unit 11 may search for a travel route from the current position to the destination using a route search algorithm such as Dijkstra's algorithm. Then, the control unit 11 controls the display 14 and the speaker 15 to execute route guidance to the destination.
[0032] The control unit 11 may interpret only the words uttered by the passenger following a specific operation or following a specific word as command words, which are words used by the passenger to control the navigation device 10. For example, the input unit 17 may include a speech button. Alternatively, the control unit 11 may cause the display 14 to display the speech button. The control unit 11 may interpret only the words uttered by the passenger after pressing the speech button as command words. Alternatively, it is assumed that the navigation device 10 is named "XYZ". The control unit 11 may interpret only the words uttered by the passenger after saying "XYZ", for example, as command words.
[0033] [2-2. Speaker registration] The control unit 11 registers passengers who have made a sound in the vehicle 30 or passengers who may make a sound. This registration is performed by storing information in a speaker database. For example, while the power of the navigation device 10 is ON, the microphone 16 may constantly collect the sound made in the vehicle 30. The control unit 11 generates a feature vector of the sound input using the microphone 16 and performs speaker recognition. For example, the control unit 11 compares the voice feature vector of a speaker already registered in the speaker database with the generated feature vector to calculate the similarity of the voice features. If the similarity is less than a predetermined value for the voices of any of the speakers already registered, the control unit 11 generates a new speaker ID. The control unit 11 may store the generated voice feature vector in the speaker database in association with the generated speaker ID.
[0034] The control unit 11 may register the passenger as a future speaker in response to an operation by the passenger. For example, the passenger selects to register the speaker by operating the input unit 17 or by inputting voice into the microphone 16. In response to this, the control unit 11 may output a message encouraging the passenger to speak, for example, a predetermined word, from the speaker 15. The passenger inputs voice into the microphone 16 in accordance with the message. The control unit 11 generates a voice feature vector based on the input voice. Then, the control unit 11 stores the new speaker ID and the voice feature vector in the speaker database. Furthermore, the passenger inputs a telephone number or an email address as the passenger's notification information destination information by operating the input unit 17, for example. The control unit 11 further stores the input notification information destination information in the speaker database.
[0035] The control unit 11 may obtain notification information destination information from a predetermined system accessible via a network such as the Internet. The predetermined system may be, for example, a system that provides some kind of service to members of the system via a network. An example of the predetermined system is a social networking service (SNS). For example, a passenger of the vehicle 30 operates a terminal device carried by the passenger to access the system using a linking application and gives permission to the navigation device 10 to access information registered in the system. Members of such a system often register their email addresses or telephone numbers in the system.
[0036] [2-3. Reporting inappropriate phrases] The control unit 11 acquires command words indicating words used to control a specific device and non-command words indicating words not used to control the specific device, based on the voice input using the microphone 16. The specific device may be, for example, the navigation device 10. For example, the control unit 11 may constantly collect voices uttered inside the vehicle 30 using the microphone 16 while the power of the navigation device 10 is ON. Then, the control unit 11 may generate word information and determine whether the word information corresponds to a command word or a non-command word, using the method described in section 2-1.
[0037] The control unit 11 stores the acquired non-command words in the storage unit 12. For example, the control unit 11 may acquire the date and time when a voice is input from the microphone 16 as the date and time of use. Then, the control unit 11 may store the non-command words and the date and time of use in the speech history database in association with each other. Here, the control unit 11 may perform speaker recognition based on the input voice. For example, the control unit 11 compares the voice feature vector of each speaker stored in the speaker database with the feature vector of the input voice to calculate the similarity of the voice features. The control unit 11 acquires the speaker ID of the speaker whose calculated similarity is equal to or greater than a predetermined value. Then, the control unit 11 may store the non-command words and the date and time of use in the speech history database in association with the acquired speaker ID.
[0038] The control unit 11 identifies a word that is used more than a predetermined number of times based on the non-command words stored in the storage unit 12. That is, the control unit 11 identifies the passenger's catchphrase. For example, the control unit 11 may calculate the number of times of use of a non-command word by counting the number of use dates and times associated with each non-command word or a specific non-command word stored in the speech history database. The predetermined number is 2 or more. For example, the predetermined number may be preset to a number of times that the word is determined to be a catchphrase. The control unit 11 may identify a word that is used more than a predetermined number of times for each speaker distinguished based on the input voice. As described above, the non-command words and the use dates and times are stored in association with each speaker. Therefore, the control unit 11 can count the number of times of use for each speaker according to this association. The control unit 11 may calculate the frequency of use of the non-command word as the number of times of use. Then, the control unit 11 may identify a word that is used more than a predetermined frequency as a catchphrase. The frequency of use may be, for example, the number of times the non-controlled word is used per a predetermined number of utterances. As described above, the utterance history database stores the duration of use of each non-command word used. Based on this duration of use, the control unit 11 may calculate the number of times each non-command word is used within the range of the most recent predetermined number of utterances as the frequency of use. Alternatively, the frequency of use may be the number of times the non-controlled word is used per a predetermined time. The control unit 11 may calculate the number of times each non-controlled word is used from, for example, a predetermined time ago to the current time as the frequency of use.
[0039] When a word identified as a word used more than a predetermined number of times corresponds to a word previously determined as an inappropriate word, the control unit 11 causes notification information indicating the identified word to be notified. That is, the control unit 11 notifies the passenger of an inappropriate catchphrase. This notification allows the speaker to know the inappropriate catchphrase. It is also expected that the notification will be an opportunity to correct the catchphrase. The control unit 11 may determine whether or not the word identified as a catchphrase corresponds to an inappropriate word based on an inappropriate word database stored in the storage unit 12. The word previously determined as an inappropriate word may be an inappropriate word stored in the inappropriate word database. The fact that the identified catchphrase corresponds to an inappropriate word may include a match between the catchphrase and the inappropriate word, or may include a similarity between the catchphrase and the inappropriate word. In this case, the similarity may include a rephrasing of the inappropriate word to the extent that the catchphrase does not change the feeling of the inappropriate word. For example, a similar word database in which similar words are associated with each other may be stored in the storage unit 12.
[0040] For example, the control unit 11 may compare each inappropriate word stored in the inappropriate word database with the word specified as the catchphrase. Then, when the word specified as the catchphrase matches any of the inappropriate words, the control unit 11 may determine that the catchphrase corresponds to an inappropriate word. Also, when the word specified as the catchphrase matches any of the words stored in the synonymous word database, the control unit 11 may acquire a synonymous word of the catchphrase from the synonymous word database. Then, when the acquired synonymous word matches any of the inappropriate words stored in the inappropriate word database, the control unit 11 may determine that the catchphrase corresponds to an inappropriate word.
[0041] The control unit 11 may output the notification information by voice from the speaker 15, or may display it on the display 14. Alternatively, the control unit 11 may transmit the notification information to a terminal device carried by the user, and cause the terminal device to notify the notification information. An example of typical notification information is "You should refrain from saying XXX." "XXX" is an identified inappropriate catchphrase. The control unit 11 may notify the notification information when an inappropriate catchphrase is identified, or may notify the notification information when an operation is performed by a passenger requesting notification of an inappropriate catchphrase.
[0042] The control unit 11 may execute either of the following, depending on the situation in which the speaker is placed, corresponding to an inappropriate word dictionary indicating an inappropriate word equivalent to the word specified as the catchphrase among the multiple inappropriate word dictionaries stored in the inappropriate word database: issuing a notification information by an output means connected to the navigation device 10, or transmitting the notification information to a terminal device other than the navigation device 10 and used by the speaker who said the catchphrase. The control unit 11 may select, as a notification source, either one of the output means connected to the navigation device 10 or the terminal device used by the speaker, by referring to a notification mode stored in the inappropriate word database in association with the inappropriate word dictionary containing the inappropriate word equivalent to the specified catchphrase. The output means connected to the navigation device 10 may or may not be included in the navigation device 10 itself. The output means may include at least one of the display 14 and the speaker 15. The control unit 11 may transmit the notification information to the terminal device by, for example, e-mail or short mail. There are roughly two situations in which the speaker is placed. Specifically, it is whether or not the person to whom the speaker's words are directed is in a place where he or she can perceive the notification information notified by the navigation device 10 (the display 14 or the speaker 15). If the person to whom the speaker's words are directed cannot perceive the notification information, there is no problem if the navigation device 10 directly notifies the person. In that case, the notification mode is set to "direct", and the control unit 11 may cause the display 14 or the speaker 15 to notify the person to whom the speaker's words are directed. On the other hand, if the person to whom the speaker's words are directed can perceive the notification information, if the navigation device 10 directly notifies the person to whom the words are directed, the person to whom the words are directed will know the speaker's inappropriate catchphrase. This may cause awkwardness between the speaker and the person to whom the words are directed. On the other hand, if the notification information is transmitted to the speaker's terminal device, basically only the speaker can confirm the notification information. In that case, the notification mode is set to "speaker terminal", and the control unit 11 may transmit the notification information to the speaker's terminal device. This will prevent the speaker and the other person from having to go through such feelings.Specifically, the notification source may be controlled depending on whether or not the person to whom the inappropriate words are directed is assumed to be aboard the vehicle 30. For example, the person to whom the inappropriate words spoken by the driver are directed is assumed to be outside the vehicle 30. Therefore, the notification mode of the inappropriate words dictionary for the driver may be set to "directly." The person to whom the inappropriate words spoken by a passenger are directed is assumed to be the driver of the vehicle 30. Therefore, the notification mode of the inappropriate words dictionary for the passenger may be set to "speaker terminal." The child to whom the inappropriate words spoken by a parent are directed is assumed to be aboard the vehicle 30. Therefore, the notification mode of the inappropriate words dictionary for the parent may be set to "speaker terminal."
[0043] Furthermore, the control unit 11 may notify notification information according to a situation corresponding to an inappropriate word dictionary indicating an inappropriate word equivalent to a word specified as a catchphrase among a plurality of inappropriate word dictionaries stored in the inappropriate word database. For example, the control unit 11 may change a message encouraging a speaker to refrain from using inappropriate catchphrases for each inappropriate word dictionary (for example, "Please calm down a little," "That may be a bit harsh for drivers," "That's a bit of an overbearing way of speaking to children," etc.). By changing the notification information according to the situation in which the speaker is placed, it is expected that the speaker will effectively stop using inappropriate catchphrases. For example, the control unit 11 may notify a message as notification information according to a notification information template stored in the inappropriate word database in association with an inappropriate word dictionary containing an inappropriate word equivalent to the specified catchphrase.
[0044] Next, a specific example will be described. As shown in Fig. 4, a person 40 is driving a vehicle 30. At this time, due to poor traffic conditions, the person 40 utters the words 110, "You're in the way," to another vehicle traveling in front of the vehicle 30. The frequency of use of the words 110 by the person 40 exceeds a predetermined frequency. The words 110 are stored in an inappropriate word dictionary for drivers. The control unit 11 outputs notification information 120, "Calm down a bit. Saying 'You're in the way' is not good," from the speaker 15 according to the notification information template and notification mode associated with the inappropriate word dictionary for drivers.
[0045] [3. Operation of navigation device] Next, an example of the operation of the navigation device 10 will be described. The control unit 11 executes the process shown in Fig. 5 according to various program codes included in the programs stored in the storage unit 12. The process shown in Fig. 5 is started, for example, when the power of the navigation device 10 is turned on.
[0046] First, the control unit 11 judges whether or not a voice has been input via the microphone 16 (step S1). If a voice has been input (step S1: YES), the control unit 11 generates a voice feature vector from the input voice signal, and generates word information indicating the spoken word by voice recognition based on the voice feature vector (step S2). Next, the control unit 11 judges whether or not the word indicated by the word information corresponds to a command word by referring to a voice command database, a genre database, a location information database, etc. (step S3). If the word indicated by the word information is a command word (step S3: YES), the control unit 11 executes a process corresponding to the command word (step S4).
[0047] On the other hand, if the word indicated by the word information is not a command word (step S3: NO), the control unit 11 acquires the speaker ID of the speaker who pronounced the word indicated by the word information from the speaker database by comparing the generated voice feature vector with the voice feature vector stored in the speaker database (step S5). Next, the control unit 11 determines whether or not the same word information as the generated word information is already stored in the speech history database in association with the acquired speaker ID (step S6). If the same word information is not already stored in the speech history database (step S6: NO), the control unit 11 stores the generated word information and the use date and time indicating the current date and time in association with the speaker ID of the specified speaker in the speech history database (step S7).
[0048] On the other hand, if the same word information is already stored in the speech history database (step S6: YES), the control unit 11 stores the use date and time indicating the current date and time in the speech history database in association with the speaker ID of the identified speaker and the same word information as the generated word information (step S8). Next, the control unit 11 calculates the use frequency of the word indicated by the generated word information based on the number of use dates and times associated with the acquired speaker ID and the same word information as the generated word information (step S9). Next, the control unit 11 determines whether the calculated use frequency is greater than a predetermined threshold (step S10). If the use frequency is greater than the threshold (step S10: YES), the control unit 11 determines whether the word indicated by the generated word information is an inappropriate word by referring to the inappropriate word database (step S11).
[0049] When the word indicated by the word information is an inappropriate word (step S11: YES), the control unit 11 identifies an inappropriate word dictionary that indicates the word indicated by the generated word information as an inappropriate word among the inappropriate word dictionaries stored in the inappropriate word database. The control unit 11 acquires an alarm information template and an alarm mode associated with the identified inappropriate word dictionary. Next, the control unit 11 determines whether the acquired alarm mode is "direct" or not (step S12). When the alarm mode is "direct" (step S12: YES), the control unit 11 embeds the generated word information in the acquired alarm information template to generate alarm information. Then, the control unit 11 converts the alarm information into a voice and outputs the alarm information from the speaker 15 (step S13). On the other hand, when the alarm mode is "speaker terminal" (step S12: NO), the control unit 11 embeds the generated word information in the alarm information template to generate alarm information. Then, the control unit 11 transmits the notification information to the terminal device of the speaker by using the notification information destination information stored in the speaker database in association with the acquired speaker ID (step S14).
[0050] If the frequency of use is less than the threshold (step S10: NO), or if the word indicated by the word information is not an inappropriate word (step S11: NO), or after steps S4, S7, S13, or S14, the control unit 11 determines whether the power of the navigation device 10 has been turned off (step S15). If the power has not been turned off (step S15: NO), the process proceeds to step S1. If the power has been turned off (step S15: YES), the process shown in FIG. 5 ends.
[0051] As described above, the navigation device 10 according to the embodiment may acquire command words indicating words used to control the navigation device 10 and non-command words indicating words not used to control the navigation device 10, based on a voice input using the microphone 16. The navigation device 10 may store the acquired non-command words in the storage unit 12. The navigation device 10 may identify words that have been used more than a predetermined number of times, based on the non-command words stored in the storage unit 12. If the identified word corresponds to a word that is predetermined as an inappropriate word, the navigation device 10 may notify notification information indicating the identified word. In this case, it is possible to make the speaker aware of an inappropriate catchphrase, if there is such a catchphrase, except for the words for controlling the navigation device 10.
[0052] Furthermore, the navigation device 10 may specify words that are used more than a predetermined number of times for each speaker who is distinguished based on the voice input using the microphone 16. In this case, inappropriate catchphrases can be notified for each speaker.
[0053] The navigation device 10 may also determine whether or not the specified word corresponds to an inappropriate word based on the inappropriate word dictionary stored in the storage unit 12. Here, the storage unit 12 may store a plurality of inappropriate word dictionaries indicating inappropriate words according to a plurality of different situations in which the speaker is placed. Then, the navigation device 10 may execute either of the following, depending on the situation corresponding to the inappropriate word dictionary indicating the inappropriate word corresponding to the specified word among the plurality of inappropriate word dictionaries stored in the storage unit 12: issuing a notification information by an output means connected to the navigation device 10, or transmitting the notification information to a terminal device other than the navigation device 10 and used by the speaker who uttered the catchphrase. In this case, depending on the situation in which the speaker is placed, it is possible to control whether or not it is acceptable for other people to know that the speaker has an inappropriate catchphrase.
[0054] The navigation device 10 may also provide notification information according to the situation corresponding to an inappropriate word dictionary that indicates an inappropriate word equivalent to the specified word, among a plurality of inappropriate word dictionaries stored in the storage unit 12. In this case, the notification information that matches the situation in which the speaker is placed can urge the speaker to refrain from using the catchphrase.
[0055] [4. Modifications] The control unit 11 may specify the situation in which the passenger who made the utterance is placed. Then, for each speaker, the control unit 11 may calculate the number of times the uttered word is used for each situation in which the speaker is placed, and determine whether the word is a catchphrase. Then, for each specified situation, the control unit 11 may use an inappropriate word dictionary corresponding to the situation among a plurality of inappropriate word dictionaries to determine whether the catchphrase is inappropriate. For example, the phrase "I thought there would be a traffic jam after all" is inappropriate when used by a passenger to a driver, but it is not necessarily inappropriate when the driver himself uses the phrase. For example, the control unit 11 may cause the camera 25 to capture the inside of the vehicle 30 while the power of the navigation device 10 is ON. Then, the control unit 11 may specify the situation in which the speaker is placed based on the image captured by the camera 25. For example, the control unit 11 specifies the passenger of the vehicle 30 using an algorithm for general object detection or estimating the posture of a human body. The control unit 11 may identify, for example, a passenger who moves his / her mouth at the same time as inputting a voice as the speaker. The control unit 11 may determine whether the speaker is the driver or a passenger based on the position of the speaker in the captured image. Specifically, the control unit 11 may determine that the speaker is the driver when the speaker is sitting in the driver's seat. On the other hand, the control unit 11 may determine that the speaker is a passenger when the speaker is sitting in a seat other than the driver's seat. The control unit 11 may also determine whether both an adult and a child are riding in the vehicle 30 based on the captured image. For example, the control unit 11 may determine whether the person in the image is an adult or a child based on the physique or face size of the person, or the positions of the eyes, nose, and mouth relative to the face. Alternatively, the control unit 11 may determine whether the speaker is an adult or a child based on a feature vector of the input voice. Then, in a situation where both an adult and a child are aboard the vehicle 30, if the adult speaks, the control unit 11 may determine that the parent (or simply the adult) spoke to the child.
[0056] When the words spoken by the passenger of the vehicle 30 as a passenger are inappropriate, the control unit 11 may determine the legitimacy of the driving or judgment by the driver. When the driving or judgment is legitimate, the control unit 11 may include information indicating that it is legitimate in the notification information. For example, the control unit 11 may search for one or more appropriate travel routes from the departure point to the destination or current location when the vehicle 30 starts moving at the actual departure time. An appropriate travel route is a route with a relatively short travel time. At this time, the control unit 11 may search for a travel route taking into account traffic congestion information, road regulation information, etc. Then, when the current travel route is included in the appropriate travel route, it may determine that the route selection by the driver is legitimate. An example of the notification information in this case is, "XXX may be a bit harsh for the driver. If you left at that time, that route would have been the best." This is expected to prevent the passenger from complaining or expressing dissatisfaction.
[0057] When the control unit 11 notifies the notification information, the control unit 11 may specify the tone of the speaker. For example, the control unit 11 may specify the tone of the speaker based on the loudness, tone, tempo, speed, intonation, etc. of the speaker's voice. Then, when the specified tone of voice is an inappropriate tone of voice, the control unit 11 may include information on the tone of voice in the notification information. The inappropriate tone of voice may include, for example, a tone of voice that makes the other person who hears the words uncomfortable. An example of an inappropriate tone of voice is a strong tone of voice. A strong tone of voice may be, for example, a loudness of voice that is greater than a predetermined value. For example, when a parent uses inappropriate words in a strong tone with respect to a child, an example of the notification information is "XXX uses words that are a little too overbearing with respect to children. It seems that the tone of voice was also a little too strong." This is expected to soften the tone of voice of the speaker.
[0058] In the above-described embodiment, the control unit 11 stores information about all non-command words in the utterance history database, and determines whether or not a non-command word that has been used more than a predetermined number of times is an inappropriate word. However, the control unit 11 may store information about only inappropriate words among non-command words in the utterance history database. Then, the control unit 11 may issue notification information when the number of times an inappropriate word is used exceeds a predetermined number of times.
[0059] The notification information may include both the specified inappropriate word and an appropriate word having the same meaning as the inappropriate word. This allows the speaker to know the appropriate way to say it. Therefore, it is expected that the speaker will appropriately correct the inappropriate phrase.
[0060] In the above-described embodiment, the notification device D according to the embodiment and the device controlled by voice are the same. However, the notification device D and the device controlled by voice may be different. For example, the notification device D may be applied to a server device capable of communicating with the navigation device 10 via a network. In this case, the navigation device 10 may be a device controlled by voice. At least one of the inappropriate word database, the speaker database, and the speech history database may be stored in the server device. The server device may obtain voice data inputted via the microphone 16 from the navigation device 10, for example, and execute the process described in the embodiment. In addition, the server device may transmit a command to the navigation device 10 to cause the navigation device 10 to notify notification information.
[0061] The notification device D may also be applied to other devices. For example, the notification device D may be applied to a smart speaker. Alternatively, the notification device D may be applied to a terminal device such as a personal computer. For example, the notification device D may be applied to a terminal device used by an operator of a call center. Inappropriate words in this case may include, for example, rude words to a customer who is talking on the phone. Examples of such words include "hello," "just in case," "can't do it," "absolutely," "thank you for your help," and "your voice is too quiet and I can't hear you." Examples of notification information include "'Your voice is too quiet and I can't hear you' is a rude way of saying that puts the responsibility on the customer. Try to say, "It seems like the phone is a little far away, can you hear me?" to confirm that both parties can hear each other's voices." The notification information may be notified after the phone call is ended. [Explanation of symbols]
[0062] 1 Acquisition method 2. Storage Control Means 3 Specific means 4 Notification control means 5 Microphone 6 Memory means D. Notification device 10 Navigation devices 11 Control section 12 Storage section 13. Communications Department 14 Display 15 Speaker 16 Microphones 17 Input section 18 Interface section 21 Vehicle speed sensor 22 Acceleration Sensor 23 Gyro sensor 24 GNSS Sensors 25 Camera 30 Vehicles
Claims
[Claim 1] an acquisition means for acquiring control word information indicating words used to control a specific device and non-control word information indicating words not used to control the specific device, based on a voice inputted using a sound input means; a storage control means for storing the acquired non-control word information in a storage means; a means for identifying a word that has been used more than a predetermined number of times based on the stored non-controlled word information; a notification control means for notifying notification information indicating the specified word when the specified word corresponds to a word that is predetermined as an inappropriate word; An alarm device comprising:
Citation Information
Patent Citations
Voice input control apparatus
JP1997311692A
Apparatus, method, and program for assisting interaction practice
JP2004309631A
Annunciation system
JP2006349843A
Telephone voice monitoring evaluation system
JP2017135642A