JPS6149130B2 - - Google Patents

Description

[Detailed description of the invention]

The present invention relates to a vehicle voice control device, and more particularly to a vehicle voice control device that controls the operation of each unit using specific spoken words. Conventionally, the operation of lights such as headlamps and equipment such as radios has been carried out by manual operation of switch devices, but with this method, the driver has to manually operate the switch device in addition to driving. It is often necessary to do so. Furthermore, when checking the vehicle's traveling speed or the time, the driver must shift his/her point of view to the gauges on the instrument panel, but this often has to be done in addition to driving operations. In view of the above, the present invention facilitates simultaneous operation or simultaneous confirmation by controlling the operation of each load using specific spoken words, improves the safety of driving operations, and is suitable for use in vehicles. An object of the present invention is to provide a voice control device. That is, the vehicle voice control device according to the present invention includes a voice recognition section that identifies a specific spoken word uttered by a driver and outputs a corresponding command signal, and a voice recognition section that inputs the command signal of the voice recognition section and operates according to the signal. and a controller that outputs a control signal to control the load. In addition, another voice control device for a vehicle according to the present invention includes a voice recognition unit that identifies a specific spoken word uttered by a driver and outputs a corresponding command signal, and a voice recognition unit that inputs the command signal of the voice recognition unit to determine the speed or speed. It is composed of a voice synthesis section that outputs status information such as time as voice. Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. FIG. 1 shows the basic configuration of a vehicle voice control device according to the present invention. The spoken word a uttered by the driver is input to the speech recognition unit 1, and its content is identified by a method described later. An 8-BIT parallel binary code b corresponding to the content of the voice is sent from the voice recognition unit 1, and the first
is input to the second decoder 2 and the second decoder 3.
This parallel binary code b is decoded by the first decoder 2 or the second decoder 3 to generate control signals C to P or r ₁ to r ₅ corresponding to the contents of the code. Here, r ₁ to _{r 5} are tuning signals that specify radio broadcast stations. The relationship between the control signals C to P and r ₁ to r ₅ outputted from each decoder 2 or 3 and specific speech words uttered by the driver is shown in the table below.

[Table] As shown in the above table, when the driver says "headlights", the control signal C appears and sets the first flip-flop 4, driving the light relay 5 and turning on the headlights. Light. Next, when you say "headlight off", the control signal d appears and the first
The flip-flop 4 is reset and the headlamp is turned off. When it says "upward", the control signal e appears, the second flip-flop 6 is set, the dimer relay 7 is driven, and the headlight is directed upward. Also, when it says "downward", the control signal f appears, the second flip-flop 6 is reset, and the headlight is directed downward. When the driver says "change course/right", the control signal g
appears, the third flip-flop 8 is set, the right turn signal relay 9 is driven, and the right turn signal flashes. When you say "go straight," the control signal h appears and the third flip-flop 8
will be reset and the right turn signal will go out. Next, when it is said to change course to the left, the control signal i appears, the fourth flip-flop 10 is set, the turn signal left relay 11 is activated, and the left turn signal flashes. When it is said to go "straight," the control signal h appears, the fourth flip-flop 10 is reset, and the left turn signal is turned off. When the driver says "wiper", a control signal j is generated, which sets the fifth flip-flop 12 and drives the wiper relay 13, thereby activating the wiper. ``Wiper off'' generates a control signal k which resets the fifth flip-flop 12 and turns off the wiper. Next, the case of speed and time confirmation will be explained. The vehicle speed sensor 14 obtains a pulse signal S whose pulse repetition frequency is proportional to the vehicle speed, and the vehicle speed detector 15 receives the pulse signal S whose pulse repetition frequency is proportional to the vehicle speed.
8BIT parallel 2 whose value corresponds to the vehicle speed
An evolved code t is generated and input to the digital multiplexer 16. Next, the 12-BIT parallel binary code u output from the digital clock 17
(the value of which corresponds to the instantaneous value of time) is also input to the digital multiplexer 16. When the driver says "speed", a control signal 1 appears, serves as a select signal for the digital multiplexer 16, and is input to the speech synthesis section 18 through the parallel binary code t. When we say "time", the control signal m appears and the digital multiplexer 16
The signal serves as a select signal and is input to the speech synthesis section 18 through the parallel binary code u. The parallel binary code t representing the speed or the parallel binary code u representing the time inputted to the speech synthesis unit 18 is decoded by the speech synthesis unit 18 and converted into a word group stored in the built-in large capacity memory. Words corresponding to this parallel binary code are selected from among them, and the audio information is automatically edited using the method described below.
A voice response v such as "52 km" or "8:47" is emitted into space and transmitted to the driver. When the driver says "radio", the second decoder 3
A control signal P is generated, the sixth flip-flop 19 is set, and the electronically tuned radio 20 is turned on. ``Radio Off'' then generates a control signal q which resets the sixth flip-flop 19 and turns the electronically tuned radio 20 OFF. When the electronic tuning radio 20 is turned on and you say "channel 1", a tuning signal _r1 appears,
NHK Daiichi is selected. When you say "channel 2", the selection signal R ₂ appears and TBS is displayed, "channel 3" appears.
Speaking of which, the selection signal R ₃ appears and shows Nippon Broadcasting Corporation, when you say "4 channel" the selection signal R ₄ appears and shows Nippon Broadcasting Corporation, and when you say "5 channel" the selection signal R ₅ appears and shows NHK. -Select each FM. Next, the functions of the speech recognition section will be explained. FIG. 2 shows the configuration of the speech recognition section 1. As shown in FIG. As shown in FIG.
, and converts it into an audio signal A, which is then transmitted to an audio amplifier 10.
1, the center frequency is amplified to a predetermined level while applying AGC (automatic gain control), and the center frequencies are respectively f 1 and f ₁ .
Eight BPFs (band pass filters) 102, 103, 104, f ₂ , f ₃ , f ₄ , f ₅ , f ₆ , f ₇ , f ₈ ,
105, 106, 107, 108, 109 and eight frequency components B ₁ , B ₂ , B ₃ , B ₄ , B ₅ , B ₆ ,
B ₇ , B ₈ , (a talk switch 99 is provided on the steering wheel 98, and when it is turned on, the microphone 100 is activated). These B ₁ to _{B 8} are connected to analog multiplexer 11
0 and a synchronizing signal C output from a microcomputer 111 as a reference, a multiplexed signal D is generated, and then inputted to an A-D converter 112, where it is converted from an analog signal to a digital signal. Parallel binary code E of the output of the A-D converter 112
is input into the microcomputer 111, and information processing is performed according to a predetermined program to extract the characteristics of the audio signal. Then, the specific words of the same driver stored in advance in the memory of the microcomputer (for example, No. 1 to No. 18 in the above table)
The voice a is identified by comparing the characteristics of the voice signal with the characteristics of the voice signal, and an 8-BIT parallel binary code b corresponding to the content of the voice a is sent out. Next, the functions of the speech synthesis section will be explained. FIG. 3 shows the configuration of the speech synthesis section 18. A parallel binary code t representing vehicle speed or a parallel binary code u representing time is input to the microcomputer 200.
The contents of the parallel binary code are decoded, a corresponding 8-BIT parallel binary code select signal F is generated, and the digital multiplexer 2 decodes the contents of the parallel binary code.
Add to 01. Digital multiplexer 20
1 input has 104 channels of memory groups 301, 302, 303, 304, 305, 3 with a capacity of 12K bytes per channel (1BITE = 8BIT).
06, . . . , 404 are connected in parallel. In each memory group, <Words stored as encoded information> 1ch memory; 301 ...... "Ji" 2ch memory; 302 ...... "Hun" 3ch memory; 303 ...... "Kiro" 4ch memory; 304 ......"Zero" 5ch memory; 305 ......"I" 6ch memory; 306 ......"D" 7ch memory; 307 ......"Sun" 8ch memory; 308 ......"Yon" : : : : 103ch memory; 403
...... "Kiyuu Jiyuu Kiyuu" 104ch memory; 404 ...... "Hiyaku" Words with a maximum word length of 2 seconds or less are each stored in the form of a binary code in the above order. Said 104
The channel memory consists of large-capacity memory (consisting of magnetic bubbles, CCD, optical memory, or ultra-LSI) with a capacity of approximately 10 MBIT. The select signal F specifies the memory channel, ie, the word, to be read and the order in which it is read. For example, if the value of the parallel binary code u is 16:02, the memories are specified in the following order: 20ch memory "Jiyu-Roku" → 1ch memory "Ji" → 6ch memory "Ni" → 2ch memory "Fun". , the word G of the 8-BIT parallel binary code is sequentially guided to the D-A converter 203 via the digital multiplexer 201, converted from a digital signal to an analog signal, and then sent to the LPF2.
04 removes the distortion and converts the answer audio signal H ("16:02
minutes"). Audio signal H is audio amplifier 2
05, the width is increased to a predetermined level, and the speaker 206
The response voice v ("16:02") is emitted into the vehicle interior. Next, the operation in the case of listening back will be explained. FIG. 5 shows the sound generating section 50. As shown in FIG. When the voice a uttered by the driver is unclear and the voice recognition unit 1 cannot identify its content, the voice recognition unit 1 sends an unclear signal w. This unclear signal w is sent to the voice generator 5.
Enter 0 and say the voice y "I wish you one more time" for asking back. When the signal w is generated, a binary code M encoding the words "I wish once again" is read out from the memory 500, and the D-A converter 5
Demodulated into an analog signal by 01, LPF502
The distortion is removed through the speaker 503, and the voice y of "I wish once again" is emitted into the space. As explained above, according to the vehicle voice control device according to the present invention, it is possible to easily operate or check multiple loads at the same time, improve the safety of driving operations, and even when installed in a vehicle due to space constraints. This is ideal because it does not particularly suffer from In the above description, the voice control device for a vehicle has been described, but it is not limited to automobiles and the like, but can be widely applied to transportation equipment such as aircraft and ships.

[Brief explanation of the drawing]

FIG. 1 is an explanatory diagram showing an embodiment of the present invention, FIG. 2 is an explanatory diagram showing a voice recognition section of the present invention, FIG. 3 is an explanatory diagram showing a voice synthesis section of the present invention, and FIG. 4 is an explanatory diagram of a steering wheel. FIG. 5 is an explanatory diagram showing one configuration example, and FIG. 5 is an explanatory diagram showing a sound generation section of the present invention. Explanation of symbols 1...Speech recognition unit, 2, 3...Decoder, 4, 6, 8, 10, 12...Flip-flop, 5, 7, 9, 11, 13...Relay, 1
4...Vehicle speed sensor, 15...Vehicle speed detector, 16...
...Multiplexer, 17...Digital clock, 18...Speech synthesis unit, 19...Flip-flop, 20...Electronic tuning radio, 98...Steering, 99...Talk switch, 100...Microphone, 101...Audio amplifier , 102-1
09...Filter, 110...Multiplexer,
111...Microcomputer, 112...A
-D converter, 200...microcomputer,
201...Multiplexer, 202...Large capacity memory, 203...D-A converter, 204...Filter, 205...Audio amplifier, 206...Speaker, 500...Memory, 501...D-A converter , 502...filter, 503...speaker.

Claims (1)

[Scope of Claims] 1. A microphone that captures specific audio words uttered by a driving vehicle, a plurality of filters that investigate the specific audio words, a multiplexer that multiplexes the outputs of the multiple filters, and a multiplexer that multiplexes the outputs of the multiplexers. It consists of an A-D converter that converts the multiplexed output into a parallel binary coded signal, and a microcomputer that identifies the voice word by comparing the parallel binary code with a pre-stored specific word, A voice recognition unit that outputs a command signal corresponding to a word, and a control unit that inputs the command signal of the voice recognition unit and outputs a control signal for controlling a load according to the signal. Vehicle voice control device. 2. A voice recognition unit that identifies a specific spoken word uttered by the driver and outputs a corresponding command signal, and a voice synthesis unit that inputs the command signal of the voice recognition unit and outputs status information such as speed or time in voice. 1. A vehicle voice control device comprising: 3. A microcomputer that decodes a command signal inputted by the speech synthesis section and outputs a word signal, a large capacity memory that stores a plurality of words to be read out in accordance with the inputted word signal, and a large capacity memory that stores a plurality of words read out according to the inputted word signal; 3. The vehicle audio control device according to claim 2, further comprising a D-A converter that demodulates the word from a digital signal into an analog signal.