JPH11143489A - Electronic equipment with sound operating function, sound operating method in electronic equipment, and automobile having electronic equipment with sound operating function - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an electronic equipment with the sound operating function, a sound operating method in the electronic equipment, and an automobile having the electronic equipment with the sound operating function capable of inputting the content to be sound-inputted by a user in a divided manner in an action of, e.g. making a call from the automobile, and informing the user of the whole input content through the sound. SOLUTION: This device is provided with a sound input means 11 to input the content through the sound by a user, a data registering means 17 to register a registered word, a sound recognizing means 10 to recognize and process the sound signal inputted in the sound input means 11, and a processing means 23 where the user can divide the content and successively input the content through the sound so that the content which is sound-inputted by the user agrees with the word registered in the data registering means 17.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an electronic device having a voice operation function capable of operating various functions by voice input, a voice operation method in the electronic device, and an automobile provided with the electronic device having a voice operation function. .

[0002]

2. Description of the Related Art In recent years, various navigation devices and the like have been proposed in which a user can operate a certain function by operating a key of a remote controller or inputting a voice. A navigation device mounted on an automobile or the like is, for example, a CD storing road map data.
A large-capacity data storage means such as a ROM (read-only memory using a compact disk), a current position detection means, and a road map near the detected current position is displayed based on data read from the data storage means; And a display device. In this case, as a means for detecting the current position, GPS (Global Position) is used.
onboarding system) or autonomous navigation that tracks changes in the current position from the starting point based on information such as the traveling direction and traveling speed of the vehicle. and so on.

The map displayed on the display device is operated not only by the operation of a key of a remote controller or the like, but also by the key operation of a remote controller or the like. Can be displayed. In the case of such a navigation device, for example, in the case of an automobile, a display device is installed near the driver's seat, and the driver can see a map near the current position while the vehicle is running or temporarily stopped such as a traffic light stop. It is common to do so.

[0004]

By the way, it has been proposed to connect a navigation device of this type to a mobile phone or a car phone, for example, and to make a call with the mobile phone through the navigation device. In this case, for example, a "call" function key in a menu displayed on the display is selected from, for example, a group of function keys of a remote controller, and then the user calls the "phone number"", It is conceivable to make a call from within a car using a mobile phone.

However, when making a call using the navigation device, the user must use the remote controller to select "make a call" from a menu on the display device, and then use the remote control. Must say "phone number" by voice input. Therefore, during driving, an "act" such as "call" in the menu on the display must be instructed, and then the "telephone number" to be called must be spoken. It is very troublesome. That is, when making a call, it is necessary to select one of the function keys of the remote controller from the function keys of the remote controller as described above, and then do not follow the procedure of saying the telephone number by voice. Can not make a phone number.

In addition, a mobile phone is mounted in a car,
By operating the keyboard of the mobile phone, the user may make a call from the mobile phone by using the mobile phone. However, in such a method of using a mobile phone, since the operation keys including the function keys of the mobile phone are arranged in a small area, each key is hard to press and which key has what function. It is difficult to recognize the displayed characters. In addition, there is also a problem that the user must read an operation manual or the like when the operation method is not understood in any case when the navigation device and the mobile phone are combined and when the navigation device is used alone. In the case where the user enters [03] for a telephone number and then enters [1234] after a while, and then enters [5678] after a while, for example, it is difficult to determine how the telephone number was entered. There is a problem that the user is difficult to understand.

Therefore, the present invention solves the above-mentioned problem, and allows the user to input contents to be input by voice input in an operation such as making a call from a car. It is an object of the present invention to provide an electronic device with a voice operation function that can notify a user of the whole by voice, a voice operation method in the electronic device, and a vehicle including the electronic device with a voice operation function.

[0008]

SUMMARY OF THE INVENTION The object of the present invention is to provide a voice input device for a user to input contents by voice, a data registration device for registering a registered word, and a voice input device. Voice recognition means for recognizing and processing the voice signal input to the means, and the user inputting the contents so that the contents input by the user match the registered words registered in the data registration means. And a processing unit capable of sequentially inputting voices in a divided manner.

In the present invention, the voice input means inputs the contents by the voice of the user. The data registration means registers the registration word. The voice recognition means recognizes a voice signal input by voice input. The processing means is adapted to allow the user to divide the content and sequentially input the voice to input the voice in order to match the content input by the user by voice with the registered word registered in the data registration means. Has become. Accordingly, it is possible to cope with a case where the user inputs the contents to be input by voice separately or a case where the contents are input collectively, and the usability by voice operation is improved. In the present invention, if the content to be input by voice is a telephone number, the telephone number can be divided and input by voice to make a call, so that it is not necessary to input voice smoothly and the usability is improved. In the present invention, it is preferable that the content divided by use is input by voice, and the processing unit repeats the content by voice for each of the divided content, and then repeats the content collectively by voice. The contents of the divided voice input can be checked collectively by voice for each divided input and after the voice input is completed.

[0010] The object of the present invention is to provide a voice recognition process for recognizing and processing a voice signal input to a voice input means by inputting voice of a user to the voice input means. And a processing step of allowing the user to divide the content and sequentially input the voice so that the content input by the user by voice matches the registered word registered in the data registration unit. This is achieved by a voice operation method in an electronic device characterized by the following. Accordingly, it is possible to cope with a case where the user inputs the contents to be input by voice separately or a case where the contents are input collectively, and the usability by voice operation is improved. In the present invention, if the content to be input by voice is a telephone number, a telephone call can be made even if the telephone number is divided and input. In the present invention, preferably, if the processing means repeats the content of voice input dividedly by use for each divided input by voice and collectively, the user can divide the voice input content by the content of the notification. Can be confirmed by voice.

[0011] The object of the present invention is to provide a vehicle equipped with an electronic device having a voice operation function in a vehicle, wherein a voice input means for a user to input contents by voice;
A data registration unit for registering a registered word, a voice recognition unit for recognizing and processing a voice signal input to the voice input unit, and a registration registered in the data registration unit for contents input by a user by voice. Processing means for allowing the user to divide the content and sequentially input speech in order to match the words,
The present invention is achieved by an automobile including an electronic device with a voice operation function, characterized by comprising: Accordingly, it is possible to cope with a case where the user inputs the contents to be input by voice separately or a case where the contents are input collectively, and the usability by voice operation is improved. In the present invention, if the content to be input by voice is a telephone number, a telephone call can be made even if the telephone number is divided. In the present invention, preferably, if the processing means repeats the content of voice input divided by use for each divided input by voice and collectively, the user can divide the voice by the content of this notification. You can check the input content by voice.

[0012]

Preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings. Note that the embodiments described below are preferred specific examples of the present invention,
Although various technically preferable limits are given, the scope of the present invention is not limited to these modes unless otherwise specified in the following description.

FIG. 1 shows an embodiment of an electronic device having a navigation function and a portable telephone function mounted on an automobile as an example of the electronic device with a voice operation function of the present invention. The electronic device 100 shown in FIG. 1 generally includes a mobile phone 101, a navigation device 20, a voice recognition device 10, and the like.

FIGS. 2 and 3 show an example in which the electronic apparatus 100 of the present invention is mounted on a car 50.
Each part of the electronic device 100 shown in FIG. First, the voice recognition device 10 and the navigation device 20 are connected to the automobile 5 as shown in FIG.
0, for example, in the rear trunk. The microphone 11 in FIG. 1 is attached to a sun visor 53 in a vehicle 50 shown in FIGS. 2 and 3. The mobile phone 101 shown in FIG. 1 is detachably set near the center console 50C of the driver's seat 52 shown in FIGS.

The speaker 32 shown in FIG. 1 is installed near the center console 50C in the driver's seat as shown in FIGS. The display device (display means) 40 of FIG.
For example, a liquid crystal display device can be used, and the display device 40 has a driver seat 52 as shown in FIGS.
Is installed on the center console 50C. The operation key 27 in FIG. 1 is provided at a column of the steering wheel 51 of the driver's seat in FIG. The antenna 21 shown in FIG. 1 is installed, for example, in a trunk 50A of an automobile 50 as shown in FIG. 2, but these antennas 21 are embedded in a rear windshield or in a side windshield. Is also good.

The engine control computer 54 of the automobile 50 shown in FIG. 2 is electrically connected to the navigation device 20 shown in FIG.
From 4, a pulse signal proportional to the vehicle speed can be supplied to the navigation device 20 side.

When the user M sits in the driver's seat 52 shown in FIG.
In addition, in the electronic device 100 of the present invention, through the navigation device 20 and the voice recognition device 10, the “target” described later and the “specific action” corresponding to the “target” can be designated only by voice input. Thus, for example, a telephone call can be automatically made to the outside. As described above, in order to specify various “objects” and “specific actions” corresponding to the “objects” by voice, the microphone 11 transmits the sun visor 53 near the front windshield glass 50B as described above. It is attached and can pick up the voice of the user M seated in the driver's seat 52. The microphone has, for example, a relatively narrow directivity, so that only the voice of the user M seated in the driver's seat 52 of the automobile 50 can be picked up satisfactorily, thereby preventing malfunction.

Next, each part of the voice recognition device 10, the mobile phone 101, the navigation device 20 and the like in FIG. 1 will be described. As described above, the electronic device 100 of the present invention includes the voice recognition device 10, the navigation device 20, the microphone 11, the display device 40, the operation keys 27, and the like. 10 and the navigation device 20 can be electrically connected. By attaching the mobile phone 101 to a bracket 50D for mounting the center console 50C of the automobile 50 in FIG. 3, the mobile phone 101 is electrically connected to the microphone 11 and the navigation device 20 as shown in FIG. Can be.

In FIG. 1, a microphone 11 is a noise filter 11 of a voice recognition device (voice recognition means) 10.
Via A, it is connected to an A / D converter (analog / digital converter) 12 and a digital audio processing circuit (DSP) 13. The digital speech processing circuit 13 is connected to a speech recognition circuit 14, and the speech recognition circuit 14
(Read only memory) 15 and a converter 16. The voice recognition circuit 14 has connection terminals 10b, 20
b, it is electrically connected to a processing means 23 such as a microcomputer of the navigation device 20.
The converter 16 is connected to the processing means 23 of the navigation device 20 via the connection terminals 10a and 20a. The conversion unit 16 is connected to a RAM (random access memory) 17.

The microphone 11 is connected to the driver's seat 52 shown in FIG.
Is a voice input unit for inputting a voice generated by the user M who is seated in the vehicle. Noise filter 11A of voice recognition device 10
Is an audio signal A input from the microphone 11
The noise of S is removed and supplied to the A / D converter 12. A
The / D converter 12 converts the audio signal AS into a digital audio signal having a predetermined sampling frequency. The digital audio signal ADS output from the A / D converter 12 is supplied to a digital audio processing circuit 13 by performing processing such as band division and filtering, using the digital audio signal as vector data and supplying the vector data to an audio recognition circuit 14. I do.

The ROM 15 stores voice recognition data, and can supply the voice recognition data to the voice recognition circuit 14. The speech recognition circuit 14 according to the vector data supplied from the digital speech processing circuit 13 and a predetermined speech recognition algorithm is performed, and a plurality of candidates are selected from the phoneme models for speech recognition stored in the ROM 15. The character data stored corresponding to the phoneme model having the highest matching degree is read out.

As the data storage state of the voice recognition data storage ROM 15, various terms such as, for example, place names, numbers, and words for instructing the operation of the navigation device 20 are stored. As the place name, for example, the names of prefectures and municipalities in Japan are stored. As numbers, data for voice recognition of numbers is stored so that telephone numbers and the like can be recognized.

The words instructing the operation of the navigation device 20 include, for example, words indicating the display position such as "destination", "departure point", "transit point", "home", and "what time" (current time). Command to ask the time), "now where" (command to ask the current position), "next" (command to listen to the next intersection),
"How much more" (command to ask the distance to the destination),
“Speed” (command to listen to current speed), “Altitude” (command to listen to current altitude), “Progress direction” (command to listen to traveling direction), “List” (list of commands that can be recognized) A character code of a word for performing various other operation commands such as a command for displaying on a display) and a phoneme model corresponding to the word are stored.

Next, the RAM 17 is a data registration unit, and stores, for example, the longitude / latitude conversion data in the conversion unit 16 described above. This RAM 17 stores the following longitude / latitude conversion data. RO for storing voice recognition data
A storage area is set for each character code having the same pronunciation as the character code of the place name stored in M15, and for each character code,
The operation when the word is recognized, the character code of the response voice, the longitude and latitude data of the region when the voice is a place name, and the data to be displayed as characters (character codes using kanji) are stored. .

In addition, the RAM 17 allows the user to register arbitrary data as a user dictionary via the processing means 23 of the navigation device 20, and also registers a basic dictionary in advance. The basic dictionary is, for example, a telephone number that has already been determined as shown in FIG. 12, for example, “police”: “110”,
“Fire department”: A target such as “119” and a telephone number can be registered. In addition, the user registration includes, for example, a “target” such as “Yamadarou” and a telephone number corresponding to the “yamadarou”, eg, “03-12”.
34-5678 "can be registered. In the registration, the user M can register in the RAM 17 through the processing means 23 by inputting voice or operating the operation key 27. The latitude and the latitude of each place name can be registered. As the longitude data, the absolute position of the location of the local government office (city hall, ward office, town hall, village office) indicated by the place name can be adopted as latitude and longitude data.

The longitude / latitude conversion data supplied from the RAM 17 and the data in the basic dictionary and the user dictionary can be supplied to the connection terminal 10a as an output from the voice recognition device 10 as voice recognition means. The contents of the basic dictionary are supplied to the processing unit 23 via the conversion unit 16 and also via the connection terminals 10a and 20a. The character code data of the voice signal recognized by the voice recognition circuit 14 is supplied to the processing means 23 through the output terminals 10b and 20b as an output of the voice recognition device 10.

Next, each component of the navigation device 20 of FIG. 1 will be described. This navigation device 2
0 has a GPS antenna 21,
Receives the positioning signal from the GPS satellite received by the current position detection circuit 22 and analyzes the received data to detect the current position. The data of the detected current position is supplied to the processing means 23 and used as data of the latitude and longitude, which are absolute positions at that time.

The processing means 23 is a circuit functioning as a system controller for controlling the operation of the navigation device 20, and includes a CD storing road map data.
-This CD-RO with a ROM (optical disk) set
A CD-ROM driver 24 for reading M stored data;
RAM 25 for storing various data necessary for data processing
And a vehicle speed sensor 26 for detecting the movement of a vehicle equipped with the navigation device, and an operation key 27 are connected. When the coordinate data of the latitude and longitude such as the current position is obtained, the processing unit 23 controls the CD-ROM driver 24 to read the road map data near the coordinate position. Then, the processing means 23 includes the CD-ROM driver 2
The road map data read in step 4 is temporarily stored in the RAM 25, and display data for displaying a road map is created using the stored road map data. At this time, the display data is set to display a map on a display scale (scale) set by operating the operation key 27 or the like.

The display data generated by the processing means 23 is supplied to the video signal generation circuit 28, and the video signal generation circuit 2
At step 8, a video signal of a predetermined format is generated based on the display data, and this video signal is supplied to the output terminal 20c.

The video signal output from the output terminal 20c is supplied to a display device (display means) 40, which performs an image receiving process based on the video signal, and displays a road map on a display panel of the display device 40. And so on.

In addition to displaying such a road map near the current position, a road map at a position designated by operating the operation key 27 or the like can be displayed based on the control of the processing means 23. . Further, based on the operation of the operation key 27 or the like, the processing means 23 performs “destination”, “departure point”, “intermediate point”, “home”, “route search”, “call”, “mark setting”. "," Nearest search "and the like can be set or registered. If you register this specific coordinate position,
Data of the registered coordinate position (longitude and latitude data)
Is stored in the RAM 17.

When the vehicle speed sensor 26 detects that the vehicle is running, the processing means 23 does not accept any operation other than the relatively simple operation of the operation keys 27.

The navigation device 20 includes an autonomous navigation unit 29, and calculates an accurate running speed of the vehicle based on a pulse signal corresponding to the vehicle speed supplied from the engine control computer 54 of the vehicle 50 in FIG. At the same time, the traveling direction is detected based on the output of the gyro sensor in the autonomous navigation unit 29, and the current position is measured by the autonomous navigation from a position determined based on the speed and the traveling direction.
For example, when the position cannot be detected by the current position detection circuit 22, the positioning by the autonomous navigation is performed from the position last detected by the current position detection circuit 22.

A speech synthesizing circuit 31 is connected to the processing means 23. If the processing means 23 needs any instruction by voice, the speech synthesizing circuit 31 executes a synthesizing process of the instructed voice, and The sound is output from the speaker 32 connected to the synthesis circuit 31. For example, various instructions necessary for the navigation device, such as "approaching the destination" and "the traveling direction is left", are performed by voice. In the voice synthesis circuit 31, the voice recognized by the voice recognition device 10 is subjected to voice synthesis processing based on the supplied character data, and is output from the speaker 32 as voice. The speaker 32 repeats, for example, the “target” or the “specific action” (see FIG. 4) input by the user M.

The navigation device 20 has input terminals 20a and 20b to which latitude and longitude data output from output terminals 10a and 10b of the voice recognition device 10 and its accompanying data and character code data are supplied. The latitude and longitude data obtained in 20a and 20b, the accompanying data and the character code data are supplied to the processing means 23.

When the latitude and longitude data D1 and the like are supplied from the voice recognition device 10, the processing means 23 controls the CD-ROM driver 24 to read road map data near the longitude and latitude from the disk. . And CD-
The road map data read by the ROM driver 24 is stored in the RAM
25, and display data for displaying a road map is created using the stored road map data. At this time, it is assumed that the supplied longitude and latitude are display data displayed at the center.

Based on the display data, a video signal is generated by the video signal generation circuit 28 and the display device 40
Then, a road map at the coordinate position designated by the voice recognition device 10 is displayed.

When the character code of a word instructing the operation of the navigation device is supplied from the output terminal 10b of the voice recognition device 10, the character code of the word instructing the operation is determined by the processing means 23. The control is performed by the processing unit 23. In this case, "destination", "departure",
When the character code of a word indicating a display position such as “intermediate place” or “home” is, the coordinates of the display position are RA
After determining whether or not the data is registered in M25, if the data is registered, the road map data near the position is stored in a CD.
-The reading from the disk is controlled by the ROM driver 24.

When data of a character code indicating the pronunciation of the recognized voice is supplied from the voice recognition device 10 to the processing means 23, the words represented by the character code are synthesized by the voice synthesis circuit 31, and the voice synthesis is performed. The sound is output from a speaker 32 connected to the circuit 31 as sound. For example,
When the voice recognition device 10 recognizes the voice as “Tokyo Bunkyo (Bunkyo-ku, Tokyo)”, based on the character string data of the recognized pronunciation, a synthesis process for generating a voice signal to be pronounced as “Tokyo Bunkyo” is performed. This is performed by the voice synthesis circuit 31, and the generated voice signal is output from the speaker 32.

In this case, in this example, the speech recognition device 1
0 when the voice recognition is performed,
And the terminal 20a is supplied with longitude and latitude data,
Although the data of the character code indicating the pronunciation of the recognized voice is supplied to the terminal 20b almost simultaneously, the processing means 2
In step 3, a process for first synthesizing the words recognized by the speech synthesis circuit 31 is executed, and then a process for creating road map display data based on longitude and latitude data is executed.

A mobile phone 101 is connected to the processing means 23 shown in FIG. For example, when the user M is directed to the microphone 11 and generates “Tokyo Tower” as an example of “object”, the user M passes through the voice recognition device 10 and
“Tokyo Tower” data is supplied to the processing means 23. R
If the "phone number" of "Tokyo Tower" as the "target" is stored in the AM 17 as the user dictionary or the basic dictionary, the "Tokyo Tower" is sent to the processing means 23 via the RAM 17 and the conversion unit 16. Is transmitted as the data TPD of the "telephone number" corresponding to. The processing means 23 sends the data TPD of the "telephone number" to the mobile phone 101, and the mobile phone 101 transmits the data TPD to the base station based on the telephone number data TPD. It is preferable to use a digital communication type mobile phone as the mobile phone 101, and the mobile phone 101 can use a 800 MHz or 1.5 GHz frequency digital phone, for example.

Next, a method of operating the electronic device 100 having the above-described navigation function and telephone function will be described. Here, the above-mentioned “target” and “specific actions” corresponding to the “target” will be briefly described. In FIG. 4, “target” defines, for example, a place to be called, for example, a place name, a station name, a landmark, a telephone number,
Items such as a mark name and a telephone registration name can be cited. Among them, the landmark refers to a prominent building or building on a map, for example, "Tokyo Tower" or the like. The telephone numbers are arranged in the order of area code-city code-number, for example, "03-1234-5678". The mark name indicates, for example, the name of the mark when the mark is set at a certain position on the display device 40 in FIG. 1 of the navigation device, and the name of the certain mark indicates, for example, the address of “Yamadarou”. This is the case. As the telephone registration name, for example, a personal name such as "Takanaka Hanako" is registered.

On the other hand, "specific action" indicates various commands, for example, "route search", "destination setting", "transit point setting", "telephone (call)", "mark setting". "," Nearest search "command, and the like.

In the embodiment of the present invention, the user M shown in FIG. 3 can first input the "target" to be called by voice, and then specify a specific "action". The designation order by such voice input is indicated by an arrow RB. Further, in the embodiment of the present invention, after the user M first specifies the "specific action" by voice input as shown by the arrow RA, the "target" is not limited to the voice input order of the arrow RB. Of course, it can also be specified.

According to the voice input procedure indicated by the arrow RB in FIG. 4, the user M specifies a "target" and then a "specific action". As an example of this, for example, after calling "Yamadarou" in "subject", say "telephone (call)" command which is "specific action",
This is a case where after calling the "target""ShinagawaStation", a "route search" command which is a "specific action" is said. On the other hand, in the case of the voice input procedure of the arrow RA, after calling the "telephone" command and then calling "Yamadarou" or the "route search" command,
This is the case when you call “Shinagawa Station”.

Next, FIG. 5 shows the portable telephone 101 and the navigation device 20 shown in FIG.
1 shows an operation example when the user M sitting in the driver's seat 52 of the automobile 50 in FIG. 1 calls outside. In FIG. 5, in step S1, the user M in FIG. 3 starts voice input to the microphone 11, and in step S2, the "landmark" which is the "object" in FIG.
If "place name" is entered, a signal is sent from the voice recognition device 10 to the processing means 23 of the navigation device 20, and the processing means 23 displays a map on the display device 40 as in step S7. As the place name in step S2, for example, "1-7-4 Konan, Minato-ku, Tokyo"
And "Tokyo Tower".

Next, in step S3, when the user M voices "here", the above-mentioned "object", for example, "Tokyo Tower" as a place name is selected and determined in step S8. When the user M inputs a "specific action" by voice, such as "call (call)" in step S4, the telephone process (step S9 in FIG. 5) shown in FIGS. 6 to 9 starts. In addition, when the user M voice-inputs “route search” as “specific action” as in step S5, the process enters a route search process as in step S91. When the user M voice-inputs "mark setting" as a "specific action" as in step S6, a mark setting process starts as in step S92.

Next, the telephone process will be described with reference to FIGS. Arrow R in FIGS. 4 and 6
There are a process of inputting voice in the direction B and a process of inputting voice in the direction of arrow RA. In the case of voice input in the direction of arrow RB in FIG. 6, the user M voice-inputs “object”, for example, “landmark (Tokyo Tower)” and further inputs “there” as a keyword. The “Tokyo Tower” is confirmed, and a “call (call)” command as a “specific action” is input by voice. In this case, since the user M has entered the keyword "there", the flag is set to "1". On the other hand, if the user M directly inputs the "call (call)" command as the "specific action" without inputting the "landmark" or "there" as described above, There are no flags.

In the case of the voice input procedure of arrow RB in the case where voice input is performed in the order of “target” to “specific action” in FIG. 4, from the start of the telephone process in step S10 in FIG. It goes through the routine of FIG. On the contrary,
Perform "object" from "specific action", that is, arrow RA
Since there is no flag in the voice input procedure, the routine of FIG. 8 passes through the arrow K from step S10 of FIG.

First, with reference to FIGS. 6 and 7, a case where the user M inputs voice along the arrow RB in the order of “target” to “specific action” will be described. In FIG. 6, the user M voice-inputs "Tokyo Tower" as the "target",
If "there" is further input as a keyword for determination, "Tokyo Tower" is voice-determined as the "target". When the user M further inputs a "call (call)" command as a "specific action", the flag is set to "1" and the telephone process in step S10 is started.

In steps S11 and S11-1 of FIG.
It is determined whether the mobile phone 101 in FIG. 1 is in the standby state. If the mobile phone 101 is in a call or is not connected to the navigation device 20, the mobile phone 101 reaches the main loop in FIG. Processing ends. In step S11, the mobile phone 1
If 01 is in the standby state, step S12
Since the "object" has already been input and determined as "Tokyo Tower" in the above, the processing moves to the routine of FIG.

After confirming that the "object" is "Tokyo Tower" in step S13 of FIG.
14, In response to this Tokyo Tower in S14-1,
The processing means 23 of FIG. 1 determines whether the telephone number of “Tokyo Tower” is registered in the RAM 17.
If the telephone number of “Tokyo Tower” is not registered in the user dictionary in advance by user registration and is not registered as a basic dictionary, the process returns to the main loop of FIG.

On the other hand, if the telephone number corresponding to "Tokyo Tower" is already registered in the user dictionary, for example, in the RAM 17 of FIG. 1 in step S14, the processing means 23 uses the speaker 32 in step S15. Say "I'll call you." In step S16, the standby time T is reset to 0 as defined by the reference symbols shown in FIG. 10, and it is confirmed in steps S17 and S18 whether the user M performs voice input. The voice input in step S17 is recognized in step S18, and the content of the voice input is determined in steps S19 and S2.
0, or a correction word, a transmission word, or a stop word as in step S21.

FIG. 11 shows an example of the correction word, the stop word, and the transmission word used by the user M. The correction word is, for example, "differential", the cancellation word is "cancel", and the transmission word is "call" or "transmission". Then, the user M determines in step S1
If, for example, a corrected word “difference” is input as a voice in step 7, the process proceeds to step S25 in FIG.

In step S19, if the corrected word is not input by voice and a transmitted word such as "call" is input by voice, the process proceeds to step S23 to perform a call operation for making a telephone call as it is, and the main operation is performed along arrow J. Return to the loop. As a result, even if the user M does not directly input a telephone number by voice input to the "Tokyo Tower" which is the "target", a telephone call to the "Tokyo Tower" can be easily and automatically input only by voice input. You can call.

Otherwise, if the user M does not input a speech word in step S20, the process proceeds to step S21. If the user M inputs a stop word such as "cancel" in step S21, The process proceeds to step S26 in FIG. 8 along the arrow F, and the processing unit 23 of the electronic device 100 cancels the process of making the call and returns to the main loop. In step S21 of FIG. 7, the user M
Is not input as "cancel" in step S22, if the standby time T has passed N seconds, for example, 5 seconds or more, that is, the user M has input at least 5 seconds of the correction word, the transmission word, and the stop word. If not, step S
At 23, the operation shifts to a calling operation for automatically making a telephone call. As a result, the processing means 23 gives the data TPD of the "telephone number" to the mobile phone 101 and transmits the data to the office. In step S22, if the user M performs voice input again in step S17 before the standby time T reaches 5 seconds, the steps in steps S18 to S22 are repeated.

In this way, as shown by the arrow PB in FIG. 6, the user M has the "target""TokyoTower","there" and the "specific action""call(call)" command. By voice input, it is possible to automatically make a call in step S23 unless correction or cancellation is performed without directly inputting the telephone number by voice.

Next, a case where the user M simply issues a "call (call)" command as shown by an arrow RA in FIG. 6 will be described. That is, the arrow R from the “specific action” in FIG.
An example in which input processing is performed along “object” along A will be described below. First, after steps S10, S11 and S12, since the flag is "1" in step S12, the process proceeds to step S24. In step S24, the RAM of FIG.
Referring to the recognition dictionary, that is, the basic dictionary (common dictionary) and the user registration dictionary (user registration word) at 17, the user M has not input the place name as the “target” yet by voice. The processing means 23 uses the speaker 32 to produce a guidance sound, "Which place do you want to call?", In step S25. Then, in step S27, the telephone number or the registered word P in FIG. 10 is cleared, the input count C is set to 0, and the standby time T is set to 0 in step S27. The input count C is a code indicating how many times a registered word registered in the RAM 17 of FIG. 1 is said. Then, the process proceeds to the step S29 shown in FIG. 8 along the arrow K. In this step S29, the user M voice-inputs, for example, the user registration word "Tokyo Tower" or "telephone number". Step S
When the recognition is performed in step 30 and "telephone number" is input in step S31, the process proceeds to the telephone number process (A) in step S32. However, if the user M has not input the voice of "telephone number" in step S31, the process proceeds to step S33.

First, the telephone number process (A) in step S32 in FIG. 8, which is a characteristic part of the embodiment of the present invention, will be described. The details of the telephone number process (A) are shown in FIG. Step S34 following step S32
In the RAM 17 of FIG. 1, a common dictionary (basic dictionary) and a telephone number (for example, a user dictionary) are referred to as a recognition dictionary, the telephone number or the registered word P shown in FIG. 10 is cleared, and the number of voice inputs B is set to 0. It is reset, and the input count is set to 0 (step S35).

Then, in response to an instruction from the processing means 23 shown in FIG.
And say for guidance. And step S37
Then, the standby time T is reset to 0, and step S38,
After confirming whether or not the user M performs voice input in S39, the voice recognition device 10 performs voice recognition in step S39. The voice input by the user M in step S40 is "telephone number, for example, 03-1234-567.
If it is 8 ", in step S41, the processing means 23 repeats for guidance and confirmation using the speaker 32. For example, the user M has the telephone number 03-1234-56.
If 78 are continuously and collectively input, step S
At 41, the song is repeated in a batch with 03-1234-5678.

Otherwise, if the user M is, for example, "03",
When "1234" and "5678" are divided and input, the steps are repeated for each division number in steps S41 and S42. That is, when the telephone number is divided and input by passing through step S42,
For example, after inputting "03", "0"
3 ", and the process returns to step S37. When the user inputs" 1234 "," 1234 "is read again in step S41, and the process returns to step S37. When input, "5678" is repeated in step S41.

Next, in step S43, the corrected word in FIG.
For example, when the user M inputs "no" by voice, in step S44, the electronic device 100 utters a guidance message "Please try again" for guidance, and step S4.
5, through step S46, step S38
In step S3, the telephone number part input by voice in
Input again in steps 7 to S40. If there is no correction word input in step S43 and there is a voice input of the calling word "call" in step S47, then in step S51 if the number of voice inputs is 1, that is, the telephone number "03-1234-56
If "78" are input collectively, step S5
3 and moves to a telephone number process (B) in FIG. On the other hand, if the voice input count B is not 1, but "03", "1234" and "5678" are voice input separately, the process goes through step S52 and what is important is that the electronic If the device 100 is "03-
1234-5678 ", and the process moves to step S53.

In the embodiment of the present invention, in the processing means of the electronic device, in order for the contents input by the user to match the registered words registered in the data registration means, Divide the content and input the voice sequentially,
Alternatively, it is possible to cope with the case where the user collectively inputs the contents by voice. If the user inputs a telephone number as a voice input, the telephone can be correctly called based on the telephone number. In addition, since the processing means can collectively notify by voice the contents that the user has divided and input by voice, the user can divide and input the contents such as a telephone number or the like by the notified contents. Even if the content is of another type, the user can surely confirm it by voice. The telephone number process (B) in step S53 is the same as step S53 in FIG.
The user M can automatically make a telephone call by performing the steps 15 to S23 in the same manner.

Returning to FIG. 9, if there is no voice input of the outgoing word in step S47, but there is a voice input of the cancel word "cancel", the process proceeds to the cancel process S100 of FIGS. 9 and 8. The process returns to the main loop via the guidance utterance process of "Call canceled" in S26.

If there is no speech input of "Cancel" in step S48 in FIG. 9, if the standby time T is shorter than N seconds (for example, 5 seconds), the process returns to step S37 and again from step S38 onward. Can make voice input. Otherwise, when the standby time T becomes 5 seconds or longer, in step S50, if the number of voice inputs B is not 0, the process proceeds to step S51, and the processing after step S51 is performed. Otherwise, if the voice input count B is 0 in step S50, it is determined that there is no voice input,
If the input count C is not 0 in step S54, the process proceeds to a cancellation process in step S100.
If the input count C is 0, the input count C is incremented by one in step S55, the process returns to step S36, and the processes in and after step S36 are performed again.

Next, returning to FIG. 8, step S31 in FIG.
In a case where the user M has referred to another registered word “target” instead of “telephone number” in S33, in step S56, for example, the registered word “Tokyo Tower” is stored in the electronic device 100.
Repeats. The “Tokyo Tower” is executed in steps S57 and S57.
At 58, the standby time T is reset to 0, and it is confirmed whether or not the user M performs voice input in step S59. The voice recognition device 10 of FIG. 1 recognizes the input voice in step S60. If the result of the recognition is “calling” which is the originating word in step S61, the voice recognition device 10 follows the arrow E in FIG. The process proceeds to the transmission process from S15 to step S23. Otherwise, if the outgoing word is not voice-inputted in step S61 and the cancel word "cancel" is voice-inputted in step S62, the electronic device 100 utters "guidance of telephone cancellation" in step S26. Return to the main loop. Step S62
In step S63, when the stop word is not speech-inputted and the correct word "no" is speech-inputted, in step S65, the electronic device 100 utters the guidance "Please again", and then follows the arrow H in FIG. Returning to step S27, the subsequent processing is performed again. Otherwise,
If the corrected word is not input by voice in step S63, and if the standby time T is less than 5 seconds, the process returns to step S59 and the user M again inputs voice. Otherwise, if the standby time T is 5 seconds or longer, the telephone call processing of steps S15 to S23 in FIG. This allows you to make a call. FIG.
Returning to step S33 in FIG. 8, if the word input by the user M in step S29 is not a registered word,
When the cancel word "cancel" is input by voice in step S66, the guidance sound is pronounced in step S26, "the call has been canceled", and the process returns to the main loop. If the stop word is not input by voice and the standby time T is within 5 seconds, the process returns to step S29, and the user M can input voice again. If the standby time T is equal to or longer than 5 seconds, the process proceeds to step S26 if the input count C is not 0 in step S67-1. Step S67-
If the input count C is 0 at 1, if the user M has never said a registered word at steps S29 to S67, at step S68, the electronic device 100 gives the following guidance to the speaker 32. This is performed using That is, in step S68, voice guidance is given, such as "Please say" name "or" telephone number "registered in mobile phone 101 and then enter the telephone number." This guidance is made in step S
When passing through the routines 29, 30, 31, 33, 67, and 68, the user M is determined to be a novice in handling the electronic device 100 of FIG. 1, and such guidance is spoken as usage guidance. Announce. Thus, the user M can perform the voice input operation again from step S28 in FIG. 6 along the arrow I according to such a procedure.

As described above, in the case of the arrow PB in FIG.
That is, a method of inputting a “specific action” after inputting a “target” by voice, and a method of inputting a “specific action” as indicated by an arrow RA.
And then enter the “target”,
It is possible to make a call using the mobile phone 101 using the navigation device 20 of the electronic device 100 of FIG. 1 only by voice input.

Next, with reference to FIGS. 13 to 19, an actual example of the act of making a voice call will be briefly described. FIG. 13 shows the state after the “target” voice input indicated by the arrow RB in FIG.
This is an example of an exchange when a “specific action” is input by voice. User M (corresponding to user) and electronic device 100
"Tokyo Tower" which is the "target"
Is input by the user M, the electronic device repeats "Tokyo Tower" for guidance and displays a map. Then, when the user M inputs a voice “to there”,
The object "Tokyo Tower" will be selected. Then, when the user speaks out a specific action, “call (make a call)”, the electronic device “calls”.
After answering with the guidance voice and waiting for 5 seconds, the call is made.

FIG. 14 shows an example of an exchange between the user (user) and the electronic device 100 when the telephone registration name of the “target” in FIG. 4 is registered as a user, for example, in “Tanakahanako”. . FIG. 15 shows a characteristic portion in the embodiment of the present invention, in which a user (user)
An example is shown in which a voice input is made while separating telephone numbers 03-1234-5678. FIG. 16 shows a characteristic part in the embodiment of the present invention, and shows an example in which the user (user) continuously and collectively inputs the telephone number as "03-1234-5678". I have. In both the case of the divided input in FIG. 15 and the case of the collective input in FIG. 16, the electronic device repeats the input content by voice. Thus, the user M can confirm the content that has been divided and input or the content that has been input collectively by voice, so that the content can be reliably input to the electronic device side. Therefore, a telephone call can be made based on the correct contents.

FIG. 17 shows an example of an exchange in the case where a user is a novice in operating the electronic device 100 when making a call using the electronic device 100 of FIG. In FIG. 17, when the user voice-inputs "telephone" like voice input,
The process of arrow RA in FIG. 6 is performed, and in step S25 in FIG. 6, when the electronic device 100 notifies the user of “Where do you want to call?” After a lapse of seconds, in step S68 of FIG.
The electronic device 100 provides voice guidance "Please say the name or telephone number registered in the telephone and then enter the telephone number." As a result, when the user voice-inputs "telephone number" for the first time, the electronic device 100 notifies the user of "please enter the telephone number" by voice. Then, the user enters "03-123
4-What? ", The electronic device 100 informs the guidance voice of whether it is" 03-1234-6578 ". If the correct number that the user wants to call is" 03-1234-5678 ", “03-1234-6578” notified by electronic equipment
Are different, the user utters “no”.
Then, the electronic device 100 guides the user with “Please try again” with the guidance voice, and thereby the user can select “03-12”.
The correct telephone number is input again by voice as “34-5678.” Then, the electronic device 100 side receives “03-1234-
Repeat 5678 "for guidance.

Next, if the user remains silent for 5 seconds, the electronic device 100 will answer "call". If the user is silent for 5 seconds, the electronic device 100 will actually return to step S23 in FIG. Start sending. By doing so, even a user who has never used the electronic device 100 of FIG. 1 can perform only a voice input operation without referring to a manual, a guidebook, or a guide displayed on a display device. You can easily and reliably make phone calls.

FIG. 18 shows an example in which the user corrects a telephone number. In this case, the user can correct the number by voice-inputting the correction word “different”. Such a correction routine can be performed by steps S43, S44, S45, and S46 in FIG. FIG. 19 shows an example of correction of the telephone registration name.

The present invention is not limited to the above embodiment. In the above-described embodiment, an example of the telephone registration name as the “target” in FIG.
A voice call is made by inputting the "target" by voice, and then by voice inputting the "specific action" of "phone (call)". However, the present invention is not limited to this. For example, after inputting "Tokyo Tower" as a landmark tower, and then inputting "telephone (call)" as a "specific action" by voice, for example, it is possible to easily call the Tokyo Tower. Can be. In addition, even if the place name, station name, telephone number, mark name, etc. of the "object" item in FIG. Can be. As a specific action, a specific action such as a route search, a destination setting, a transit point setting, a mark setting, or a nearest search can also be designated.

On the contrary, it is of course possible to input a specific action shown in FIG. 4, for example, "telephone (call)" by voice, and then call a "target", for example, a telephone registered name. After inputting the route search, destination setting, transit point setting, mark setting, and nearest search setting of the specific action first, the place name, station name,
Of course, landmarks, telephone numbers, mark names or telephone registered names can be called.

In the illustrated embodiment, an example is described in which a portable telephone is set for a navigation device mounted on a car and a call is made from the inside of the car to the outside by the portable telephone. However, not limited to this, other types of electronic devices, for example, the electronic device with a voice operation function of the present invention is not limited to the illustrated ordinary passenger car, the present invention,
For example, it can be mounted on other types such as an airplane and a ship. Not only electronic devices of the type that are mounted and moved, but also electronic devices of the type set at a certain place as fixed devices, similarly, for example, when performing other types of functions without being limited to the function of making calls, The present invention is applicable.

The electronic apparatus of the present invention is not limited to an example in which a navigation device is combined with a mobile phone, but may be applied to a combination of a mobile phone and a television set, or a combination of other audio equipment and a telephone. . An embodiment of the present invention provides a telephone or a car navigation system with a telephone having a voice recognition function, when a user utters several digits of a telephone number, and repeats the portion in a fragmented manner every time the voice is recognized. At the same time, voice interface processing can be performed in which all digits of the recognized telephone number are passed through and all the digits are read at once and then auto-dial.

[0077]

As described above, according to the present invention,
For example, in an operation such as making a call from a car, the user can separately input the content to be input by voice input, and even when the user inputs separately, the entire input content can be notified to the user by voice. From this, the user can confirm the contents, and can reliably perform the operation by the voice operation.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a preferred embodiment of an electronic device with a voice operation function of the present invention.

FIG. 2 is an exemplary perspective view showing an example of an automobile including the electronic device of FIG. 1;

FIG. 3 is an exemplary perspective view showing the inside of the automobile shown in FIG. 2;

FIG. 4 is a diagram showing an example of “object” and “act” in the present invention.

FIG. 5 is a view showing a process of making a call from a place name by voice input in the electronic apparatus of the present invention.

FIG. 6 is a diagram showing a part of a flow for a user to make a telephone call only by voice input.

FIG. 7 is a view showing a flow following FIG. 6;

FIG. 8 is a view showing a flow following FIGS. 6 and 7;

FIG. 9 is a telephone number process (A) associated with FIGS. 7 and 8;
FIG.

FIG. 10 is a diagram showing definitions of reference numerals in FIGS. 6 to 9;

FIG. 11 is a diagram showing an example of a correction word, a stop word, and a transmission word.

FIG. 12 is a diagram showing an example of a registered word, a basic dictionary, a user dictionary, and a telephone number identification word.

FIG. 13: “Specific action” after voice input of “target”
FIG. 4 is a diagram showing an example of inputting a voice.

FIG. 14 is a diagram illustrating an example of making a call when “target” is a registered word.

FIG. 15 is a diagram showing a case where a user inputs voice by separating telephone numbers.

FIG. 16 is a diagram showing a procedure for making a call when a user inputs a telephone number collectively by voice.

FIG. 17 is a diagram showing an example in which a beginner makes a telephone call by saying a telephone number.

FIG. 18 is a diagram showing an example of correcting a telephone number.

FIG. 19 is a diagram showing an example of a case where a registered word is corrected.

[Explanation of symbols]

10 ... voice recognition device (voice recognition means), 11 ...
Microphone (voice input means), 17 ... RAM
(Data registration means), 20 ... navigation device,
23 ... processing means, 40 ... display, 100
... Electronic equipment, 101 ... Mobile phone

Continued on the front page (51) Int.Cl. ⁶ Identification code FI G08G 1/0969 G08G 1/0969 H04M 1/27 H04M 1/27

Claims (9)

[Claims] 1. A voice input means for a user to input contents by voice, a data registration means for registering a registered word, and a voice recognition for recognizing and processing a voice signal input to the voice input means. Means, and processing means for allowing the user to divide the content and sequentially input the voice so that the content input by the user by voice matches the registered word registered in the data registration means. An electronic device having a voice operation function. 2. The electronic device with a voice operation function according to claim 1, wherein the content input by voice by the user is a telephone number. 3. The contents that the user divides and inputs by voice,
The electronic device with a voice operation function according to claim 1, wherein the processing unit repeats the voice by voice for each of the divided contents, and then repeats the voice collectively by voice. 4. The electronic device with a voice operation function according to claim 1, wherein the electronic device is a navigation device including a mobile phone for making a call. 5. A voice recognition processing step of recognizing and processing a voice signal input to the voice input means by the voice recognition means by inputting a voice of the user to the voice input means; A processing step in which the user can divide the content and sequentially input the voice to input the content so that the content matches the registered word registered in the data registration unit. Voice operation method. 6. The voice operation method for an electronic device according to claim 5, wherein the content input by voice by the user is a telephone number. 7. The contents which the user divided and input by voice,
2. The voice operation method in an electronic device according to claim 1, wherein the processing unit repeats the voice by voice for each of the divided contents, and then repeats the voice by voice collectively. 8. A vehicle equipped with an electronic device having a voice operation function in a vehicle, wherein a voice input means for a user to input contents by voice, a data registration means for registering a registered word, and a voice input means. Speech recognition means for recognizing and processing the input speech signal And a processing unit capable of sequentially inputting voice. 9. A vehicle equipped with the electronic device with a voice operation function according to claim 8, which is a navigation device provided with a mobile phone for making a call.