JP2016099479A - Voice control system, voice control method, and voice control program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a voice control system, a voice control method, and a voice control program capable of easily performing the desired control of a user.SOLUTION: A voice control system includes: a microphone 3 for receiving the input of a voice; and a control part 8 for continuing the same control or switching the type of control in accordance with the length of the ending of the voice received by the microphone 3. Especially, the control part 8 includes a steadiness determination control part 8a for determining whether or not the voice is steadily input by the microphone 3, and the control part 8 continues the same control since it is determined that the voice is steadily input by the steadiness determination control part 8a until it is determined that the voice is not steadily input by the steadiness determination control part 8a.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a voice control system, a voice control method, and a voice control program.

  Conventionally, in a vehicle-mounted navigation device, a system that accepts an instruction such as scroll speed adjustment in display information such as a map has been proposed. In such a conventional system, the scroll speed is adjusted according to the time during which the user continuously presses the scroll button with a finger, the length of the user flicking the touch panel, and the like. However, in this conventional system, the operation with a finger is troublesome, and the operation cannot be performed when both hands are closed. In view of this, a system that recognizes a user's voice and performs a scroll operation has been proposed as a system that enables easier scrolling speed adjustment and the like (see, for example, Patent Document 1). Specifically, in this system, the speed is divided into a plurality of stages (for example, “high speed high”, “high speed”, “medium speed”, “low speed”, “low speed”), When the user utters “fast” while scrolling the map by operating the cross key or touch panel, the system recognizes and analyzes this sound and responds to the analyzed sound. Thus, the scrolling speed can be increased by one step (for example, from “medium speed” to “high speed”).

JP 2005-221244 A

  However, the voice input system as in Patent Document 1 has the advantage that the troublesomeness caused by the operation with the finger is eliminated, and the operation is possible even when both hands are closed, Depending on the type of parameter to be operated, the user may not be able to easily perform desired control. That is, in the technique according to Patent Document 1, it is necessary to divide parameters such as speed into a plurality of stages. However, continuous parameters such as scroll speed and scroll movement amount are classified into a plurality of stages. As a result, the continuity of the parameters is impaired, and there is a possibility that the user cannot easily perform the desired control. For example, in the technology according to Patent Document 1, if the speed is divided into a relatively large number of stages, it is not possible to perform an easy input because it is necessary to input a voice many times until the user achieves a desired speed. If the speed is divided into relatively small stages, there is a possibility that the speed desired by the user cannot be set. Therefore, there has been a demand for a system that can easily perform user-desired control while taking advantage of voice input.

  The present invention has been made in view of the above, and an object of the present invention is to provide a voice control system, a voice control method, and a voice control program capable of easily performing a user's desired control by voice input. And

  In order to solve the above-described problems and achieve the object, a voice control system according to the present invention includes a voice input receiving unit that receives a voice input, and a length of a voice ending that is received by the voice input receiving unit. And control means for continuing the same control or switching the type of control.

  In addition, the voice control method according to the present invention continues the same control according to the voice input reception step of receiving voice input and the length of the ending of the voice received in the voice input reception step, or A control step of switching the type of control.

  In addition, the voice control program according to the present invention continues the same control according to the voice input acceptance process for accepting voice input and the length of the ending of the voice accepted in the voice input acceptance process, or And causing the computer to execute a control step of switching the type of control.

  According to the voice control system, the voice control method, and the voice control program according to the present invention, the same control is continued or the control type is switched according to the length of the voice ending. It is possible to easily perform the desired control. In particular, even in the case of controlling continuity parameters such as scroll speed and scroll movement amount, it is not necessary to divide the parameters into a plurality of stages. Desired control can be easily performed.

It is a block diagram which illustrates the voice control system concerning an embodiment of the invention. It is a table | surface which shows the control audio | voice information stored in the control audio | voice table. It is a flowchart of an audio | voice control process.

  Hereinafter, embodiments of a voice control system, a voice control method, and a voice control program according to the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to the embodiments.

[Basic concept of the embodiment]
First, the basic concept of the embodiment will be described. This embodiment generally relates to a voice control system that receives and controls a user's voice input. The voice control system can be applied to various devices that can be controlled based on a user's voice input. However, in the present embodiment, the voice control system is applied to a vehicle-mounted navigation device (hereinafter referred to as a vehicle-mounted device). It will be described as a thing. However, for example, the same voice control system can be suitably applied to devices in a field completely different from on-vehicle devices such as smartphones, portable navigation devices, air conditioning devices, video devices, and audio devices.

  Here, in the present embodiment, when the user performs voice input of the control content, there is a case where the utterance is extended and the utterance is uttered. In this case, the extended ending portion is expressed as “˜”. I will explain. Here, the “end of word” is the last word (syllable) uttered by the user, but when the last word is composed of a plurality of sounds (for example, consonants and vowels), It means the last sound. For example, in the case of a Japanese word, since the last sound of one word is a vowel, this vowel becomes the “end of word”. Specifically, when the user utters a Japanese “right” ending, the sound corresponding to “right” is “Migi”, and the last word (syllable) uttered by the user is “ It is "gi". And since the last sound of this “gi” is the vowel “I”, the ending is “I”. In this case, it is written as “right”.

[Specific contents of the embodiment]
Next, specific contents of the embodiment will be described.

(Constitution)
In the present embodiment, a case where the in-vehicle device functions as a voice control system by installing a voice control program in the in-vehicle device will be described. In addition, as described above, for example, a voice control system is configured by installing a voice control program in any device including, for example, a smartphone, a portable navigation device, an air conditioner, a video device, or an audio device. May be. Moreover, since the function as the vehicle-mounted device in the voice control system can be obtained by the same configuration as that of a known vehicle-mounted device, the description thereof will be omitted, and in the following, particularly the configuration for achieving the voice control explain. In the following description, a specific vehicle (a vehicle on which a user operating the in-vehicle device is mounted) equipped with this voice control system will be simply referred to as “vehicle”. “Vehicle” includes an automobile, a motorcycle, and a bicycle. Hereinafter, a case where the vehicle is an automobile will be described.

(Constitution)
First, the configuration of the in-vehicle device 1 will be described. FIG. 1 is a block diagram illustrating a voice control system according to this embodiment. As shown in FIG. 1, the in-vehicle device 1 generally includes a speaker 2, a microphone 3, a touch panel 4, a display 5, a current position acquisition unit 6, a communication unit 7, a control unit 8, and a data recording unit 9. Yes.

(Configuration-Speaker)
The speaker 2 is sound output means for outputting information by sound based on the control of the control unit 8. The specific form of the sound output from the speaker 2 is arbitrary, and it is possible to output a synthesized sound generated as necessary and a sound recorded in advance.

(Configuration-microphone)
The microphone 3 is one of a plurality of input means for receiving various inputs, and is a voice input receiving means for receiving voice input. As the microphone 3, a known microphone can be used.

(Configuration-touch panel)
The touch panel 4 receives various manual inputs from the user when pressed by a user's finger or the like. The touch panel 4 is formed to be transparent or translucent, and is provided on the front surface of the display 5 so as to overlap the display surface of the display 5. As this touch panel 4, for example, a publicly known touch panel provided with operation position detecting means by a resistance film method or a capacitance method can be used.

(Configuration-Display)
The display 5 is a display means for displaying an image guided by the voice control system, and in particular, displays a map based on map information stored in a map database (hereinafter referred to as “DB”) 9a described later. Display means. The specific configuration of the display 5 is arbitrary, and a flat panel display such as a known liquid crystal display or organic EL display can be used.

(Configuration-Current position acquisition unit)
The current position acquisition unit 6 is current position acquisition means for acquiring the current position of the vehicle. For example, the current position acquisition unit 6 knows the current position (coordinates) and direction of the in-vehicle device 1 detected by at least one of a GPS, a geomagnetic sensor, a distance sensor, or a gyro sensor (all not shown). Get by the method.

(Configuration-Communication Department)
The communication unit 7 is a communication unit that performs communication with a center device (not shown) via a network. The specific type and configuration of the communication means are arbitrary. For example, a known mobile wireless communication means or a known VICS (registered trademark) system wireless communication means via FM multiplex broadcasting or beacon is used. be able to.

(Configuration-control unit)
The control unit 8 is a control unit that controls the in-vehicle device 1, and in particular, a control unit that continues the same control or switches the type of control according to the length of the ending of the voice received by the microphone 3. It is. Specifically, the CPU, various programs that are interpreted and executed on the CPU (including basic control programs such as an OS and application programs that are activated on the OS to realize specific functions), programs, and various data It is a computer configured with an internal memory such as a RAM for storing. In particular, the voice control program according to the present embodiment is substantially installed in the in-vehicle device 1 via an arbitrary recording medium or network, thereby substantially configuring each unit of the control unit 8.

  The control unit 8 includes a steady state determination control unit 8a and a voice analysis unit 8b in terms of functional concept. The steady state determination control unit 8a is a steady state determination control unit that determines whether or not sound is constantly input from the microphone 3. The voice analysis unit 8 b is a voice analysis unit that analyzes the voice received by the microphone 3. Specific processing performed by each unit of the control unit 8 will be described later.

(Configuration-Data recording part)
The data recording unit 9 is a recording unit that records a program and various data necessary for the operation of the in-vehicle device 1, and is configured using, for example, a hard disk (not shown) as an external recording device. However, any other recording medium including a magnetic recording medium such as a magnetic disk or an optical recording medium such as a DVD or a Blu-ray disk can be used instead of or together with the hard disk. The data recording unit 9 includes a map DB 9a, an utterance example DB 9b, and a control voice table 9c.

  The map DB 9a is map information storage means for storing map information. Here, “map information” is information necessary for specifying various positions including roads, road structures, facilities, and the like. For example, node data (node numbers, coordinates, etc.) relating to each node set on the road. ), Link data related to each link set on the road (link ID, link name, start side connection node number, end side connection node number, road coordinates, road type (for example, toll road, general road, etc.), road It includes information, feature data (signals, road signs, guardrails, facilities, etc.), and terrain data.

  The utterance example DB 9b is utterance example storage means for storing utterance example information for specifying the content of the user's input voice. Specifically, this utterance example DB 9b stores the spectrum information of the control voice and the spectrum ID that uniquely identifies each spectrum information in association with each other. Here, the “spectrum information” is information used for voice analysis of the voice analysis unit 8b, for example, information derived by Fourier analysis of voice information (WAV information). In addition, the “control voice” is a voice with an extended ending including the detailed control contents (for example, “up”, “lower”, etc., hereinafter “control contents”) for the in-vehicle device 1. “Up”, “Down”, “Right”, “Left”, “Enlarged”, “Reduced”, “Left”, “Right”, “Left”, “Right” The term “rotation” is applicable. That is, in the prior art, since the user usually does not utter the utterance, the spectrum information of the voice that does not extend the utterance is stored in order to specify the user's input voice. Specifies the content of the input voice when the user utters with the word ending extended, and thus stores the spectrum information of the voice with the word ending extended in this way. A specific method for specifying the content of the input voice will be described later. “Spectrum ID” is identification information assigned to each control voice (“Up”, “Down”, “Right”, etc.), for example, “0001”, “0002”, A serial number such as “0003”. The timing of storing these utterance example information in the utterance example DB 9b is arbitrary. For example, the utterance example information may be stored in advance at the time of factory shipment, or from the transmission center (not shown) via the communication unit 7 at the time of program update or the like. Information may be received and stored. Further, learning may be performed with reference to voice input by the user, and the spectrum information stored in the utterance example DB 9b may be corrected to information suitable for the user, or new spectrum information may be added.

  The control sound table 9c is control sound storage means for storing control sound information. FIG. 2 is a table showing the control sound information stored in the control sound table 9c. As illustrated in FIG. 2, information corresponding to the item “command name”, the item “spectrum ID”, and the item “control voice” is stored in the control voice table 9 c in association with each other.

  Here, the information stored corresponding to the item “command name” is information indicating the type (command) of control executed by the voice control system, and is displayed on the display 5 as shown in FIG. “Map Scroll” which is a command for scrolling the map in a specific direction, “Map Scale” which is a command for changing the scale of the map displayed on the display 5, and a command for rotating the orientation of the map displayed on the display 5 A “map direction”, a “list scroll” that is a command for scrolling a list of destination candidates, and a “volume” that is a command for changing the volume of the speaker 2 are stored.

  The information stored corresponding to the item “spectrum ID” is a plurality of spectrum IDs corresponding to the item “command name” among the spectrum IDs stored in the utterance example DB 9b.

  Further, the information stored corresponding to the item “control voice” is a control voice uniquely specified by each spectrum ID. The timing for storing the control voice information in the control voice table 9c is arbitrary. For example, the control voice information may be stored in advance at the time of factory shipment, or the communication unit 7 may be connected from a transmission center (not shown) at the time of program update or the like. The information may be received and stored via

(Voice control processing)
Next, a voice control process executed by the voice control system configured as described above will be described.

  This voice control process is generally a process of continuing the same control or switching the type of control according to the length of the voice ending input by the user. A process for controlling the display content of the display 5 of the in-vehicle device 1 according to the length of the vehicle will be described. The timing for executing this voice control process is arbitrary. For example, in the present embodiment, the on-vehicle apparatus 1 is automatically turned on when the vehicle-mounted device 1 is turned on and set to a specific command mode by the user. It will be explained as a thing. The command mode is a mode for executing a specific command. For example, five modes corresponding to the item “command name” of the control voice table 9c are “scroll mode”, “map scale mode”. ”,“ Map orientation mode ”,“ List scroll mode ”, and“ Volume mode ”are selected and set by the user. The method for setting the command mode is arbitrary. For example, the user may set the command mode by operating the touch panel 4 with a finger. Further, the user inputs “scroll mode” or “map scale mode” or the like via voice through the microphone 3, and the input voice is set by the control unit 8 to analyze the input voice. Also good. In addition, since the specific structure and method of the voice analysis for setting the command mode in this manner are known, detailed description thereof will be omitted. In the following description, it is assumed that the command mode is set to “scroll mode”.

  FIG. 3 is a flowchart of the voice control process. First, in SA1, the control unit 8 determines whether or not the amplitude of the sound input to the microphone 3 is equal to or greater than a threshold value. Although the specific method of this determination is arbitrary, for example, a known digital vibration sensor may be provided in the in-vehicle device 1 and the amplitude of sound input via the microphone 3 may be measured by this digital vibration sensor. . Note that the threshold value can be set to an arbitrary value, but may be set to an amplitude comparable to that of a voice during a normal conversation of a person, for example.

  If the amplitude is not greater than or equal to the threshold value (SA1, No), it is assumed that there is no voice input by the user, and the process waits until the amplitude exceeds the threshold value by repeating SA1. If the amplitude is equal to or greater than the threshold (SA1, Yes), it is assumed that there is a voice input by the user, and the process proceeds to SA2.

  In SA2, the control unit 8 starts voice input recording. Specifically, the voice input through the microphone 3 by the user is recorded in the data recording unit 9 as needed. Although the specific method of this recording is arbitrary, for example, audio information (for example, WAV information) is recorded in the data recording unit 9.

  Next, in SA3, the stationary determination control unit 8a determines whether or not the user's voice has become stationary. “Stationary” refers to a state in which substantially the same sound is repeated continuously over a reference time (for example, 0.5 seconds). This is the case where the time has been extended. For this determination, a known method can be adopted. For example, the speech information recorded in the data recording unit 9 is Fourier-analyzed to derive spectrum information, and the spectrum of the same speech in the derived spectrum information is the latest from the current time. When the reference time is repeated continuously, it may be determined that the end of the voice is extended by the reference time (that is, the user's voice has become steady). In addition, although the specific determination method and numerical value of reference | standard time are arbitrary, for example, when a user utters a voice without intending to extend the ending of the voice, the longest time that the same voice is repeated continuously is determined. It is obtained by experiment etc., and the time exceeding this maximum time is set as the reference time. Further, it may be determined based on information other than the above-described spectrum information, for example, whether it is steady or not, for example, based on audio information before Fourier analysis (for example, WAV information). good. For example, when the amplitude of the audio information itself is in a convergence state, for example, for a reference time (for example, 0.5 seconds), it may be determined that the sound information has become steady.

  And when it is not steady (SA3, No), for example, when “U” or “E” is input in the voice “up to”, etc., by repeating SA3, Wait until On the other hand, when it becomes steady (SA3, Yes), for example, when the voice of the ending part “˜” is inputted in the voice “up”, the process proceeds to SA4.

  In SA4, the voice analysis unit 8b analyzes the voice information recorded in the data recording unit 9, and specifies the voice input by the user. More specifically, the voice analysis unit 8b analyzes the voice information input via the microphone 3 to obtain spectrum information, and the initial part of the spectrum information (a steady input at SA3 after the voice input is started). The portion up to the point where it is determined that the input speech is determined) is compared with the spectrum information of the control speech stored in the utterance example DB 9b, and the input speech is specified by searching for a speech that substantially matches. As described above, conventionally, it is normal to analyze a portion from when the sound is input until the sound is interrupted, but in the present embodiment, until the sound becomes steady after the sound is input. However, since the utterance example DB 9b stores the spectrum information of the control voice with the ending, the input voice can be suitably specified. Note that the analysis of voice information may be performed not by comparing spectrum information as described above but by comparing WAV information.

  Next, in SA5, the voice analysis unit 8b determines whether or not the voice input by the user is a control voice corresponding to the set command. Specifically, first, the speech analysis unit 8b refers to the utterance example DB 9b and identifies the spectrum ID of the speech identified in SA4. Next, the voice analysis unit 8b refers to the control voice table 9c, and whether the spectrum ID specified as described above is included as the scroll ID corresponding to the command of the set mode (scroll mode in the present embodiment). Determine whether or not. When the voice analysis unit 8b determines that the spectrum ID corresponding to the set command is not included, the voice input by the user is not a control voice corresponding to the set command (SA5, No). The voice control process ends. When the voice analysis unit 8b determines that the spectrum ID corresponding to the set command is included, the voice input by the user is assumed to be a control voice corresponding to the set command (SA5, Yes). Move to SA6.

  In SA6, the control unit 8 executes control. Specifically, the control unit 8 identifies the set command mode (“scroll mode” in the present embodiment), and the control content (“up” in the present embodiment) indicated by the control voice identified in SA4. And specific control is executed based on these two. For example, in the present embodiment, the control unit 8 scrolls the map displayed on the display 5 upward by a reference amount at a reference speed.

  Next, in SA7, the stationary determination control unit 8a determines whether or not the user's voice is still stationary. For example, it is determined whether or not the ending part of the voice “upper” is still repeated regularly. However, a specific method of this determination can be described in the same manner as SA3, and thus the description is omitted. And when it determines with it being steady (SA7, Yes), after performing the same control again in SA6, it is determined whether it is steady again in SA7. That is, as long as the user continues to extend the ending, the same control is continuously executed in SA6 by repeatedly executing the processes in SA6 and SA7. As a result, for example, the map displayed on the display 5 can continue to move upward. In this embodiment, the second and subsequent scrolls are also moved at the same speed as the first scroll. However, the present invention is not limited to this, and the second and subsequent scrolls are increased or decreased each time control is repeated. It doesn't matter. This is the end of the description of the voice control process.

[Modifications to Embodiment]
Although the embodiments of the present invention have been described above, the specific configuration and means of the present invention may be arbitrarily modified and improved within the scope of the technical idea of the present invention described in the claims. Can do. Hereinafter, such a modification will be described.

(About problems to be solved and effects of the invention)
First, the problems to be solved by the invention and the effects of the invention are not limited to the above contents, and may vary depending on the implementation environment and details of the configuration of the invention. May be solved, or only some of the effects described above may be achieved. For example, even if the user's desired control cannot be easily performed by voice input, the user's desired control can be performed by a technique different from the conventional technique. Has been resolved.

(About distribution and integration)
Further, each of the electrical components described above is functionally conceptual and does not necessarily need to be physically configured as illustrated. In other words, the specific forms of distribution and integration of each unit are not limited to those shown in the drawings, and all or a part thereof may be functionally or physically distributed or integrated in arbitrary units according to various loads or usage conditions. Can be configured. For example, the in-vehicle device 1 is configured to be distributed among a plurality of devices configured to be able to communicate with each other, and a steady state determination control unit 8a is provided in a part of the plurality of devices, and another one of the plurality of devices. A voice analysis unit 8b may be provided in the unit.

(About shape, numerical value, structure, time series)
Regarding the constituent elements exemplified in the embodiment and the drawings, the shape, numerical value, or the structure of a plurality of constituent elements or the mutual relationship in time series may be arbitrarily modified and improved within the scope of the technical idea of the present invention. Can do.

(About control details)
Although the present embodiment has been described as performing the upward scrolling as the control content, the processing can be continued for the other control content according to the length of the ending of the input voice of the user. For example, the downward direction, the left direction, the right direction, the upper right direction, the upper left direction, and the like can be described in the same manner as in the embodiment. In addition, other commands can be explained in the same manner. For example, in the case of a map scale command, when there is a voice input such as “enlargement to” or “reduction to” by the user, it depends on the length of the ending. It is possible to control to enlarge or reduce the map scale at a constant speed. At this time, the speed of enlarging or reducing may be increased according to the length of the ending. Moreover, you may comprise as a system which controls apparatuses other than the apparatus (this embodiment in-vehicle apparatus 1) comprised as an audio | voice control system. For example, the in-vehicle device 1 and the air conditioner mounted on the vehicle are linked to each other, and the air temperature of the air conditioner is fixed at a constant speed according to the length of the ending of the input voice of the user “raise up”. It is also possible to perform control to increase the air volume.

  In the present embodiment, only five types of commands are specified, but other commands can be added to the control voice table 9c as appropriate and described in the same manner. For example, a “brightness adjustment command” that adjusts the brightness of the display 5 in response to a voice input such as “upper” or “lower” or an air conditioner in response to a voice input such as “hot” or “cold” Even if you apply “air volume adjustment command” that adjusts the air volume of the vehicle, or “window adjustment command” that adjusts the opening of the vehicle window according to the voice input such as “open ~” or “close it ~” I do not care.

  Further, in the present embodiment, it has been described that the same control is continued according to the ending length of the voice input by the user. However, the present invention is not limited to this, and the control is performed according to the ending length of the voice input. It is good also as what switches a kind. For example, the set command mode may be switched at a predetermined time interval in response to a voice input “mode˜”. That is, the present invention is not limited to controlling continuous parameters, and non-continuous parameters and commands may be controlled.

(About control voice)
In this embodiment, voice input is performed after the command mode is set, but these may be performed simultaneously. Specifically, voices such as “scrolling up” and “scrolling down” are stored as control voices in the utterance example DB 9b, and when a similar voice input is made by the user, the scroll mode is set. However, the upward scrolling may be continued according to the length of the ending. According to such control, setting of the command mode can be omitted.

  Further, in the present embodiment, the voice with the ending of the control content such as “upper”, “lower”, etc. is applied as the control voice, but is not limited thereto. For example, the control may be continued or the type of control may be switched according to the ending of a simple voice “A” or “I” that does not include control content. Specifically, when the voice "A ~" is input, the map is scrolled upward according to the length of the ending, and when the voice "I ~" is input, You may comprise so that a map may be scrolled below according to length.

[Characteristics and effects of the embodiment]
Finally, some of the features and effects of the embodiments described so far are exemplified below. However, the features and effects of the embodiment are not limited to the following contents, and only some of the following effects are achieved by including only a part of the following features, or other than the following features. By providing the characteristics, there may be other effects than the following effects.

  The voice control system according to one aspect 1 of the embodiment performs the same control according to the voice input receiving unit that receives voice input and the length of the ending of the voice received by the voice input receiving unit. Control means for continuing or switching the type of control.

  According to the voice control system according to aspect 1, the same control is continued or the type of control is switched according to the length of the voice ending, so that the user can easily perform desired control by voice input. Things will be possible. In particular, even in the case of controlling continuity parameters such as scroll speed and scroll movement amount, it is not necessary to divide the parameters into a plurality of stages. Desired control can be easily performed.

  In the voice control system according to another aspect 2 of the embodiment, in the voice control system according to the aspect 1, the control unit determines whether the voice is constantly input by the voice input reception unit. A stationary judgment control means for judging, wherein the control means judges that the voice is steadily input by the steady judgment control means after the voice is steadily inputted by the stationary judgment control means. The same control is continued until it is determined that no input has been made.

  According to the voice control system according to the aspect 2, when a control voice including the control contents is input, the control contents indicated by the control voice are continued according to the length of the end of the control voice. However, the trouble of inputting the control contents by other means can be omitted, and the control contents can be instructed more simply.

  The voice control system according to another aspect 3 of the embodiment is the voice control system according to the side face 1 or the side face 2, further comprising voice analysis means for analyzing the voice received by the voice input acceptance means, When the voice analysis unit analyzes that the voice is a control voice including the control content, the means continues the control content indicated by the control voice according to the length of the ending of the control voice.

  According to the voice control system according to aspect 3 described above, the same control is continued from when it is determined that the voice is steadily input until it is determined that the voice is not steadily input. Therefore, it is possible to continue the same control according to the time during which the sound is regularly repeated, and easy control for the user is possible.

  In the voice control system according to another aspect 4 of the embodiment, in the voice control system according to any one of the side face 1 to the side face 4, the control means controls an in-vehicle device mounted on the vehicle.

  According to the voice control system according to the above aspect 4, since the control means controls the in-vehicle device mounted on the vehicle, even when the hand cannot be released such as when driving the vehicle, the user can make a voice. Easy operation according to the length of the ending is possible.

  In the voice control method according to the other aspect 5 of the embodiment, the same control is performed according to the voice input acceptance process for accepting voice input and the length of the ending of the voice accepted in the voice input acceptance process. And a control step for switching the type of control.

  According to the voice control method according to the aspect 5, the same control is continued or the type of control is switched according to the length of the voice ending, so that the user's desired control can be easily performed by voice input. Things will be possible. In particular, even in the case of controlling continuity parameters such as scroll speed and scroll movement amount, it is not necessary to divide the parameters into a plurality of stages. Desired control can be easily performed.

  The voice control program according to the other aspect 6 of the embodiment performs the same control according to the voice input acceptance process for accepting voice input and the length of the ending of the voice accepted in the voice input acceptance process. A control step of continuing or switching the type of control.

  According to the voice control program according to the above aspect 6, the same control is continued or the type of control is switched according to the length of the voice ending, so that the user's desired control can be easily performed by voice input. Things will be possible. In particular, even in the case of controlling continuity parameters such as scroll speed and scroll movement amount, it is not necessary to divide the parameters into a plurality of stages. Desired control can be easily performed.

DESCRIPTION OF SYMBOLS 1 In-vehicle apparatus 2 Speaker 3 Microphone 4 Touch panel 5 Display 6 Current position acquisition part 7 Communication part 8 Control part 8a Steady state determination control part 8b Voice analysis part 9 Data recording part 9a Map DB
9b Utterance example DB
9c Control voice table

Claims (6)

Voice input receiving means for receiving voice input;
Control means for continuing the same control or switching the type of control according to the length of the ending of the voice received by the voice input receiving means,
Voice control system. The control means includes
A stationary judgment control means for judging whether or not the voice is constantly inputted by the voice input receiving means;
The control means until the steady judgment control means judges that the voice is not constantly inputted after the steady judgment control means judges that the voice is constantly inputted. The same control is continued during
The voice control system according to claim 1. Voice analysis means for analyzing the voice received by the voice input reception means,
When the voice analysis unit analyzes that the voice is a control voice including control content, the control means continues the control content indicated by the control voice according to the length of the ending of the control voice. ,
The voice control system according to claim 1 or 2. The control means controls an in-vehicle device mounted on the vehicle.
The voice control system according to any one of claims 1 to 3. A voice input receiving process for receiving voice input;
A control step of continuing the same control or switching the type of control according to the length of the ending of the voice received in the voice input reception step,
Voice control method. A voice input receiving process for receiving voice input;
In accordance with the length of the speech ending received in the voice input reception step, the same control is continued, or the control step of switching the type of control,
Voice control program for causing a computer to execute.

Images