JPS5870285A - Voice recognition equipment for vehicle - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

[Detailed Description of the Invention] The present invention provides voice registration when there is a large amount of noise in the vehicle interior.
The present invention relates to a voice recognition device for a vehicle, which has the following characteristics.

2. Description of the Related Art Recently, voice recognition devices have begun to be used in various industrial fields, which recognize commands and information input by voice and determine whether or not the voice is voice. The voice of this food WtwI&
In the device, voices are registered in advance and compared with the input voice to determine whether the voice is a hit or miss.

FIG. 11 is a block diagram of this type of conventional speech recognition device. In the figure, 1 is a microphone that inputs a voice command, 2 is a voice recognition unit that registers or recognizes voice based on the voice command signal from microphone 1, and 3 is voice%.
! ! A registration switch that puts the Oribe 2 into the registration mode, and a power supply voltage is supplied to the Audio G Oribe 2 via the ignition switch from the 4-digit battery power source.

In the above voice recognition device, when the user gets in the vehicle and turns the ignition switch to the ACC (accessory) position, a source voltage is supplied from the power source 4 to the voice signal S2 via the diode 5. After that, K to register the voice is the registration switch 3.
The voice recognition unit 2 is turned on to put the voice recognition unit 2 into the registration mode, and the voice to be registered in the microphone IK is inputted, thereby registering the voice in the voice recognition unit 2.

In such voice recognition devices, while the vehicle is running, not only the engine sound is always heard, but also sounds from fans, radios, and audio equipment may also be heard. In addition, when the sunroof or windows are opened while driving, noise from outside the vehicle enters the interior of the vehicle, so when registering audio, those noises are superimposed on the audio, and due to the influence of that noise, the appropriate There is a problem in that there is no choice but to register. During such mF
This problem occurs not only when the SM vehicle is running but also when it is stopped. Also, when registering multiple words, the order of registration is determined in advance.
Some vehicles have a K display, but in such cases, registration is done while looking at the display panel while driving, which is not good for driving.

The present invention was made in view of the above points.

In order to prevent tk from registering voice when the noise inside the vehicle is large, the registration operation is prohibited when it is detected that the noise inside the vehicle increases.

Based on the drawings below, the present invention fI! 52 will be revealed.

#! FIG. 2 is a block diagram showing an embodiment of the dual-use speech recognition device according to the present invention. In the figure, the same reference numbers as w1 figure indicate the same inspection line part, and this example is 11
The difference from the conventional example shown in the figure is that an inverter 6 and an AND circuit 7 are provided; one input terminal of the AND circuit 7 is connected to the registration switch 3, and the other input terminal is connected to the registration switch 3 via the inverter 6. The output terminal of the AND circuit 7 is connected to the audio g* section 2.

Next, the operation of this embodiment will be explained.

First, when the ignition switch is placed in the ACC position, the voice recognition section 2 is supplied with power supply voltage. At this time, since no signal is output from the ignition-on position (hereinafter abbreviated as IGN-ON position), the signal output from the IGN-ON position becomes L (Iffl) level and is passed through the inverter 6 to the AND circuit 7. H (High) to one input terminal
Input as a level signal. The edge registration switch 3
When f is turned on, the KH level signal from the other input terminal of the AND circuit 7 is input, so the AND condition of the AND circuit 7 is satisfied and its output becomes qH level. As a result, the voice recognition unit 2 enters the registration mode, and by inputting voice to the microphone 1, the voice recognition unit 2 registers the voice.

Next, turn the ignition switch to the IGN-ON position.
The output from the GN-ON position becomes the FiH level and is input to one input terminal of the AND circuit 7 via the inverter 6, so even if the registration switch 3 is turned ON in this state, the AND condition of the AND circuit 7 is still met. Therefore, the voice recognition s2 does not go into the registration mode, and as a result, no voice registration is performed in the voice recognition@2.

In this way, the ignition switch ff I GN-ON
In other words, when the engine is running (there is engine noise), the voice cannot be registered, which improves the recognition rate.

FIG. 3 shows another embodiment of the dual-use speech recognition device according to the present invention, in which the R8 freetub flop 8
The set terminal S of the R8 flip-flop 8 is connected to the registration switch 3, and the reset terminal R is connected to the OR circuit 9 to register the 10N-ON position of the power source s4 and the registration of the voice recognition unit 2. It is also connected to the output terminal Q of the R8 flip-flop 8 and the voice recognition section 1 (S2). Also in this embodiment, when the ignition switch is set to the ACC position, the Power supply voltage is supplied. ζNow, when the registration switch 3 is turned on, 8 R8 flip-flops are set, so its Q output becomes H level, and as a result, the voice recognition section 2 enters the registration mode and inputs voice to the microphone 1. Then, voice registration is performed by and.After that, voice 1 [
When the registration is completed in ll12, a registration end signal is output, and the R8 flip-flop 8 is reset via the OR circuit 9, so its Q output becomes L level, and as a result, the voice recognition il & part 2 registration mode ends. do.

During registration, turn off the ignition switch OFF I GN -O
When it is set to the N position, the R8 flip 70 knob 8 is reset via the OR circuit 91, so the registration mode of the voice recognition wR section 2 is interrupted and the voice registration ends midway, but the voice is not registered. Next, before registering the audio, if the ignition switch fYrIGN is set to the ON position, the OR circuit 9f
rounding, through which the R8 flip-flop 8 is reset;
After that, even if the registration switch 3 is turned on, the voice recognition unit 2 does not change to the registration mode and cannot register the voice.

In this way, the ignition switch fIGN is turned on during voice registration.
- As soon as the switch reaches the ON position, the registration mode ends and no further registration is possible.

Also, the registration mode ends every time the audio is registered, so even if you open a window and the noise level in the room increases, you will not be able to register.

The recognition rate can be further improved than the embodiment shown in FIG.

The above-mentioned embodiment describes a case where the noise level inside the vehicle increases due to the engine noise when the engine is activated by the ignition switch, but this is the case where the noise level inside the vehicle increases. Besides fans, radio.

Since the audio system may be activated or the sunroof or window may be opened, the present invention detects when the noise level inside the vehicle increases and prohibits the registration operation. Good too. In addition, if the item that increases the above noise level is operated by supply from the battery by detecting all the states of the ignition switch, the ignition switch is turned on and off.
It is good to detect F, but in the case of a sunroof or window that is manually opened/closed, it is better to detect from the movement of the sunroof and windows that the noise level inside the vehicle has increased.

Micropon is installed 1 in the above vehicle voice recognition device.
1. Since there are restrictions on rfI, 1. Normally, it is necessary to install sun visors, roofs, spotlights, etc. at a position quite far away from the passenger's mouth (30 to 80 CII), so when Moka is driving in a tunnel. When voice recognition is performed under such conditions, such as when driving at high speed or at high speeds, the noise may cause erroneous recognition and reduce the recognition rate. Therefore, it is preferable to provide an additional microphone in addition to the microphone provided at the above position. Figure 4 is a block diagram of an embodiment of a voice recognition system equipped with two microphones.In the figure, 10 is a device installed in a position far away from the passenger's mouth, such as a sun visor, roof, or spotlight. 11 is an amplifier for amplifying the audio signal (100) from the microphone 10; 12 is an auxiliary microphone attached to a position close to the mouth, such as at the collar of the passenger's jacket; Signal (120) t - an amplifier for amplifying; 14 is a signal (110) from amplifier 11 and a signal from amplifier 13 (
130), and 15 is a voice recognition Rs that performs voice recognition based on the signal (140) from the changeover switch 14. Figure 5 shows an example of the cutter x4 cutter 14 shown in Figure 4.

The changeover switch 14 is provided by a jack 16, an auxiliary microphone plug 17, and an auxiliary microphone plug 17.

In the embodiment shown in Figure 4, when voice recognition is performed during normal driving, the auxiliary microphone plug 17 is connected to the jack as shown in Figure 5 (A). Remove it from 16. At this time, contact 18
Since the terminals 8 and 8/i are in contact as shown, the terminals 8 and 8/i are electrically connected. In this way, the sound is transferred to the microphone 10.
When input to , the audio signal from microphone 1o (100
) is amplified by the amplifier 11 to become a signal (110), which is input to the speech recognition unit 15 as a signal (140) by the changeover switch 14, so that speech recognition is performed.

Next, if you want to perform voice recognition when the noise is relatively high, such as when driving in a tunnel or at high speed, insert the auxiliary micro plug 17 into the jack 16 as shown in Figure 5. The auxiliary microphone 12 is fixed to the collar of the passenger's jacket with a clip or the like. At this time, since the contact 1Stj separates as shown in the figure, the terminals S and 8' are electrically disconnected. When the audio is input to the auxiliary microphone 12, the audio signal from the auxiliary microphone 12 (12
0) is amplified by the amplifier 13 and appears as a signal (130), which is input to the speech recognition s15 as a signal (140) by the changeover switch 14, so that speech recognition is performed.

As described above, since the auxiliary microphone 12 is located closer to the passenger's mouth than the microphone 10, the gain of the amplifier 13 is set to be smaller than the gain of the amplifier 11. If the auxiliary microphone 12 is used to input voice when the noise level is high, the recognition rate will be improved because the noise level input to the voice recognition unit 15 will be lower than when the microphone 10 is used.

As explained above, in the present invention, when it is detected that the noise in one room is increasing, the registration operation is prohibited, so that appropriate registration can be performed without being affected by noise. can improve the recognition rate. According to the present invention, since there is no need to perform registration while driving, there is no need to look at the display panel for registration while driving, which is favorable for driving.

[Brief Description of the Drawings] Figure #1 is a block diagram of a conventional speech recognition device. Figure 2 is a block diagram showing an embodiment of the dual-purpose voice recognition device according to the present invention, Figure 3 is a block diagram showing another embodiment of the dual-purpose voice recognition device according to the present invention, and Figure 4 is a block diagram showing another embodiment of the dual-purpose voice recognition device according to the present invention. 2.
FIG. 5 is a block diagram showing an embodiment of a single-use voice recognition device provided with two microphones, and FIG. 5 shows an embodiment of the changeover switch shown in FIG. 4. 1.10% 12...Microphone, 2%15...
Voice recognition unit, 3... Registration switch, 4... Denshu s,
6...Inverter, 7...AND circuit, 8...R
8 flip-flops, 9...OR circuit, 11.13.
...Amplifier, 12...Auxiliary microphone. 14... Selector switch, 16... Jack. 17...Auxiliary microphone plug patent applicant Hiroo Tsuchi Suzuki, attorney for Nissan Motor Co., Ltd. Figure 1 Figure 2 Figure 3 Figure 4rlA Figure 5

Claims (1)

[Claims] (11) In a voice recognition device having a command means that is operated when commanding voice registration and a voice recognition means that enters a voice registration mode when the command means is operated, the noise level in the vehicle interior increases. A dual-use audio device comprising: a noise detection device that outputs a registration prohibition signal when it detects that the registration prohibition signal is detected; and a registration prohibition device that prohibits voice registration when the registration prohibition signal is output. Recognition device. (2) The internal audio a-telephone device according to claim #I1, wherein the noise detection means is a means for detecting an on state of an ignition switch.