close

Вход

Забыли?

вход по аккаунту

JP2006094389

код для вставкиСкачать
Patent Translate
Powered by EPO and Google
Notice
This translation is machine-generated. It cannot be guaranteed that it is intelligible, accurate,
complete, reliable or fit for specific purposes. Critical decisions, such as commercially relevant or
financial decisions, should not be based on machine-translation output.
DESCRIPTION JP2006094389
PROBLEM TO BE SOLVED: To provide an in-vehicle conversation assistance device in which
conversation can be clearly heard regardless of the position of a passenger in a motor vehicle.
SOLUTION: A flat condenser device array is installed on a ceiling in a car. The device at the
specific position functions in advance as a microphone, and when speech speech is recognized,
the device near the speaker functions as a microphone. This makes it possible to reliably collect
conversational speech. Also, the output gain adjustment is performed independently for each
device functioning as a speaker. As a result, even if the number of devices functioning as a
speaker increases or decreases, conversational voice can be produced at a constant volume. In
addition, a human sensor may be installed in a car so that a device in the vicinity of the occupant
in the vehicle functions as a microphone and a device in the vicinity of the listener functions as a
speaker when speech speech is recognized. This enables more efficient conversation assistance.
[Selected figure] Figure 1
In-car conversational aid device
[0001]
The present invention relates to a conversation assistance device in a motor vehicle, and more
particularly to a conversation assistance device that forms a sound field by a microphone and a
speaker mounted in the vehicle.
[0002]
2. Description of the Related Art In recent years, passenger cars are equipped with devices for
09-05-2019
1
generating sounds such as car audio and car navigation in the car, and there is a situation where
conversations between occupants can not be heard.
In addition, while driving on an expressway, road noise from car engine tires, tires and wind
noise became louder, making it difficult to catch conversations.
[0003]
Therefore, a plurality of conversation assistance devices have been proposed so that
conversations between crew members can be clearly heard.
[0004]
In Patent Document 1, a microphone and a seating sensor are installed in each seat in a car, and
the in-vehicle conversation assistance device sets the output level for each speaker according to
the position of the speaker and changes the direction in which the conversation voice is heard
Has been proposed.
[0005]
Patent Document 2 proposes an automatic gain adjustment device capable of performing gain
control after suppressing noise and listening at an appropriate volume according to the distance
between a speaker and a microphone.
JP-A-2002-51392 JP-A-9-311696
[0006]
However, the in-vehicle conversation assistance device described in Patent Document 1 includes
a microphone for each seat, and detects whether an occupant is seated and performs sound field
control, so that, for example, a flat where three persons can sit in parallel In the case of a seat or
the like, appropriate sound field control can not be performed because the seating position is
vague.
[0007]
The automatic gain adjustment device described in Patent Document 2 always supplies a
09-05-2019
2
constant sound pressure level to the sound generation part (speaker etc.), and there is a problem
that it becomes difficult to hear when the listening side is away from the speaker installation
position.
[0008]
An object of the present invention is to provide a speech aid device that can clearly hear speech
regardless of the position of the occupant.
[0009]
The invention according to claim 1 includes a sound collection element array in which a plurality
of sound collection elements functioning as a microphone or a speaker by switching are arranged
on a ceiling of a car, a sound collection element functioning as a microphone, and a speaker
Switching means for switching the sound collecting element to be operated independently for
each sound collecting element, voice recognition means for recognizing conversational voice
from the sound collected by the sound collecting element functioning as a microphone, and each
seat in the car The switch means is instructed to place a plurality of sound collecting elements
near the position or in the car ceiling in advance as sound collecting elements to function as a
microphone, and conversation is started from the sound collected by the sound collecting
elements functioning as the microphone When the voice is recognized, release it to act as a
microphone depending on the volume or recognition position of this conversational voice And
control means for instructing the switching means to change the number and arrangement of the
sound elements, characterized by comprising a.
[0010]
In the present invention, planar capacitor type devices that function as microphones or speakers
by switching are installed in the form of an array on the interior ceiling of a car.
A plurality of planar capacitor-type devices near each seat or in a car are preset to function as
microphones.
When a passenger in a car talks, the number and arrangement of flat capacitor type devices
operated as a microphone are changed according to the volume and position of the detected
speaker.
09-05-2019
3
[0011]
The invention according to claim 2 includes a plurality of human sensors for detecting the
position of the occupant, and the control means causes a part of the sound collection elements
near the occupant detected by the human sensors to function as a microphone. The switching
means is instructed to change the arrangement to a sound collection element, and the sound
collection element other than the area near the occupant detected by the human sensor is
changed to a arrangement to change a sound collection element to function as a speaker It is
characterized by instructing.
[0012]
According to the present invention, in the above-described invention, the number and the
arrangement of the flat condenser type device to function as a microphone are changed
according to the arrangement of the occupant detected by the human sensor.
Therefore, conversational speech can be collected reliably.
Further, by operating the flat condenser type device other than the vicinity of the occupant
detected by the human sensor as a speaker, it is possible to efficiently emit sound to the listener.
[0013]
The invention according to claim 3 further comprises gain control means for independently
controlling the gain for each sound emitting element, wherein the control means causes the
sound collecting element near the listener to function as a speaker. It is characterized in that the
element is set as the element and the gain control means is set to increase the gain of the sound
collecting element in the direction of the speaker.
[0014]
In the present invention, in the above invention, the gain of each planar capacitor type device is
controlled independently.
09-05-2019
4
A planar capacitor type device near the listener acts as a speaker and increases the gain towards
the speaker.
This allows the voice to be heard from the direction of the speaker.
[0015]
As described above, according to the present invention, a plurality of flat capacitor type devices
can be arranged in a panel shape on a car ceiling, and connection of each device can be switched
to be used as a microphone or a speaker. The number and arrangement of speakers and speakers
can be easily changed according to the position of the speaker or the listener, and the
conversation voice can be efficiently transmitted to the listener regardless of the position of the
speaker .
[0016]
Hereinafter, the in-vehicle conversation assistance device according to the embodiment of the
present invention will be described in detail with reference to the drawings.
FIG. 1 is a schematic view of a car equipped with the in-vehicle conversation assistance device of
the present embodiment.
The figure (A) is the schematic which looked at the motor vehicle from the side, and the figure (B)
is the schematic in the motor vehicle. As shown in the figure, a planar capacitor device array 1 is
installed on a ceiling in a car. The in-vehicle conversation assistance device according to the
present embodiment transmits conversational speech to the listener by collecting the speech of
the talker by the flat condenser device array 1 installed on the ceiling, adjusting the gain in the
car and pronouncing it in the car. It is a thing.
[0017]
The interior of the motor vehicle is provided with a right front seat S11, a right rear seat S12, a
left front seat S21, and a left rear seat S22. An occupant (driver) H11 is seated on the seat S11,
and an occupant H12 is seated on the seat S12. Also, the seat is not limited to two rows for two
09-05-2019
5
as shown in the figure, and may be an automobile equipped with more seats.
[0018]
FIG. 2 is a diagram showing the configuration of a planar capacitor device array. As shown in the
figure, the planar capacitor device array 1 includes n devices D11 to D1 n, n + 1 devices D21 to
D2 n + 1, and n devices D31 to D3 n, which are arranged without any gap. And n + 1 devices D41
to D4n + 1. In the row of devices D11 to D1 n, each device of the planar capacitor device array 1
is arranged in the order of devices D11 to D1 n in the row of devices D11 to D1 n in the row of
devices D21 to D2 n + 1 in the row of devices D21 to D2 n + 1. ... D2n + 1 are arranged in the
order of devices D31 to D3n in the order of devices D31 to D3n, and in order of devices D41,
D42,..., D4n + 1 in the case of devices D41 to D4n + 1 ing.
[0019]
Further, each row is composed of a device array row consisting of devices D11 to D1n, a device
array row consisting of devices D31 to D3n, a device array row consisting of devices D21 to D2n
+ 1, and a device array row consisting of devices D41 to D4n + 1 The center position of the
device is shifted by 1/2 of the length of the device in the longitudinal direction of the vehicle.
That is, as the whole planar capacitor device array 1, each device is arranged in a zigzag form.
[0020]
Here, all of the devices except the devices D21, D2n + 1, D41, and D4n + 1 are formed by a
substantially square planar capacitor device, which is a basic shape. On the other hand, the
devices D21, D2n + 1, D41 and D4n + 1 are formed in a substantially rectangular shape which is
a half of the substantially square, that is, in a half size of a basic shape. The ends of the devices
D11, D21, D31, and D41 in the front direction of the vehicle coincide with each other, and the
ends of the devices D1n, D2n + 1, D3n, and D4n + 1 coincide with the rear of the vehicle. Is
rectangular. The rectangular planar capacitor device array 1 is installed on a ceiling in a car.
[0021]
09-05-2019
6
Furthermore, here, the flat condenser device is a sound collection element that functions as a
microphone or a speaker by switching. That is, in the flat type capacitor device in the present
embodiment, when an audio signal is input, the diaphragm vibrates due to the attraction and
repulsive force generated between the electrodes in the internal electrode to generate an acoustic
wave. Further, when the diaphragm is vibrated by receiving the sound wave from the outside, it is
possible to take out the audio signal by the change in the capacitance generated by the vibration.
[0022]
The figure (A) is a figure at the time of making devices D11-D1n and D41-D4n + 1 function as a
microphone, and the figure (B) makes the devices D12, D1 n-1, D43, and D4 n function as a
microphone. Of the As shown in FIG. 6A, one or more rows can all function as a microphone, and
as shown in FIG. 7B, a device at a specific position can function as a microphone. In the figure (B),
the device near each seat is made to function as a microphone. Thus, each device can function as
a microphone or a speaker by individual switching.
[0023]
FIG. 3 is a block diagram showing the configuration of the in-vehicle conversation assistance
device of the present embodiment. As shown in the figure, the in-vehicle conversation assistance
device includes a planar capacitor device array 1 having the above-described configuration, and
switches SW11 to SW4n + 1 connected to the respective devices D11 to D4n + 1 of the planar
capacitor device array 1, The voice recognition unit 3 and the gain adjustment unit 5 respectively
connected to the respective switches, and the switching control unit 4 for performing the
operation control of the respective switches are provided. The in-vehicle conversation assistance
device also includes the control unit 2 that controls the operation of the voice recognition unit 3,
the gain adjustment unit 5, and the switching control unit 4.
[0024]
The switches SW11 to SW1n, SW21 to SW2n + 1, SW31 to SW3n, and SW41 to SW4n + 1
correspond to the devices D11 to D1n, D21 to D2n + 1, D31 to D3n, D41 to D4n + 1 constituting
the planar capacitor device array 1, respectively. Connected Further, each switch connects each
device to either the voice recognition unit 3 or the gain adjustment unit 5 in response to a
09-05-2019
7
switching instruction from the switching control unit 4. This allows each device to function as a
microphone or speaker. The device functioning as a microphone transmits a sound wave received
from the outside to the voice recognition unit 3 as a voice signal. The device functioning as a
speaker outputs the audio signal output from the gain adjustment unit 5 to the outside as a
sound wave.
[0025]
The voice recognition unit 3 analyzes a voice signal input from a device functioning as a
microphone through a switch, and determines whether the input voice signal is a conversation
voice. The analysis method compares, for example, the input audio signal with an audio signal
pattern stored in advance in a memory (not shown) or the like. Here, the comparison method
uses, for example, a probability model such as a hidden Markov model. By recognizing only the
conversational speech from the device functioning as the microphone, it is possible to recognize
that the passenger in the car has uttered.
[0026]
The control unit 2 controls the operations of the voice recognition unit 3, the gain adjustment
unit 5, and the switching control unit 4 as described above. The control unit 2 causes the device
at the specific position to function as a microphone as an initial state of the in-vehicle
conversation assistance device. For example, as shown in FIG. 2A, the switch control unit 4 is
instructed to cause the devices D11 to D1n and D41 to D4n + 1 to function as a microphone.
That is, by using the in-vehicle ceiling two rows as a device that functions as a microphone, it is
possible to identify in which area of the vehicle the conversation voice is generated. Furthermore,
the control unit 2 instructs the switching control unit 4 to temporarily function as a microphone
the periphery of the device with the largest voice input level when recognizing the conversational
voice. As a result, the voice of the speaker can be collected reliably and efficiently.
[0027]
Further, for example, as shown in FIG. 2B, the switching control unit 4 may be instructed to cause
the devices D12, D1n-1, D43, and D4n to function as a microphone. That is, devices in the
vicinity of each seat may be made to function in advance as microphones. Furthermore, the
control unit 2 may instruct the switching control unit 4 to temporarily cause the periphery of the
09-05-2019
8
device that has recognized the conversational voice to function as a microphone.
[0028]
In addition, when collecting speech of the speaker, the sound collection timing of each device is
individually changed so that the directivity of the sound collection becomes the direction of the
speaker, and the sound signal collected by each device is collected. You may make it synthesize ¦
combine. This makes it possible to reliably collect only the speaker's speech.
[0029]
The gain adjustment unit 5 adjusts the output gain of the sound to be produced by the device
functioning as a speaker. The gain adjustment unit 5 can perform gain control independently for
each device. The control unit 2 sets the gain adjustment unit 5 to perform gain adjustment
dynamically according to the number of devices that function as speakers. For example, when the
number of devices functioning as speakers is small, the output gain of each device is increased so
as not to reduce the overall output gain. As a result, it is possible to produce speech at a constant
volume as a whole.
[0030]
Also, output gain adjustment may be performed according to the position of the speaker. For
example, the output gain is increased in order from the device functioning as a speaker near the
listener to the direction of the speaker. This allows the voice to be heard from the direction of the
speaker.
[0031]
Note that an audio signal of a car audio or the like (not shown) may be connected to be input to
the gain adjustment unit 5. In this case, when the controller 2 does not recognize a conversation,
it instructs the gain adjustment unit 5 to produce sound of the car audio from the device
functioning as a speaker, and when the speech is recognized, the controller 2 generates the
music of the car audio. It may be instructed to lower the volume and give priority to speaking
09-05-2019
9
voice.
[0032]
FIG. 4 is a block diagram of the in-vehicle conversation assistance device further provided with a
human sensor. This in-vehicle conversation assistance device further includes a human sensor 6
in addition to the above-mentioned in-vehicle conversation assistance device. The human sensor
6 detects the presence of an occupant in a motor vehicle, and for example, installs a plurality of
infrared sensors in the vehicle to identify where in the vehicle the occupant is seated. The human
sensor 6 transmits the detected position information of the occupant to the control unit 2. The
control unit 2 instructs the switching control unit 4 to change the arrangement of the device that
functions as a microphone according to the position information of the occupant. For example,
when the human sensor 6 detects the presence of an occupant near the devices D12, D1n-1, D43,
and D4n in the planar capacitor device array 1 shown in FIG. 2B, the devices D12, D1n-1, D43 ,
And D4 n function as a microphone. At this time, when the occupant moves, the control unit 2
instructs the switching control unit 4 to change the arrangement of the device that functions as a
microphone. For example, when it is detected that an occupant in the vicinity of the device D43
has moved to the vicinity of the device D33, the device D43 functions as a speaker and the device
D33 functions as a microphone. This enables reliable speech recognition.
[0033]
Furthermore, when speech speech is recognized in each device, the control unit 2 instructs the
switching control unit 4 to cause the device near the speaker to function as a microphone. As a
result, the voice of the speaker can be collected reliably and efficiently. Further, the device at a
position where an occupant other than the speaker is present instructs the switching control unit
4 to function as a speaker. For example, when it is recognized that an occupant in the vicinity of
the device D43 emits a conversational voice, the devices D32, D33, D42, D44, etc. function as
microphones, and the devices D12, D1n, and D4n temporarily function as speakers. This makes it
possible to reliably transmit the speaker's speech to the listener.
[0034]
FIG. 5 is a flow chart showing the operation of the in-vehicle conversation assistance device in
the present embodiment. First, it is determined whether each device functions as a microphone
09-05-2019
10
or as a speaker (s1). Here, as described above, one row or a plurality of rows may all function as
a microphone, or a device at a specific position may function as a microphone. Moreover, in the
case of the in-vehicle conversation assistance device provided with the human sensor 6,
arrangement ¦ positioning of the device made to function as a microphone according to
positional information is determined.
[0035]
After that, it is determined whether the conversational speech has been recognized (s2). Here, as
described above, the voice signal input from the device functioning as the microphone is
analyzed to determine whether it is conversational voice. When it is determined to be
conversational voice, the arrangement of the device functioning as a microphone and the device
functioning as a speaker are changed (s3). In the change of arrangement, a device functioning as
a microphone is arranged in the vicinity of a recognized device of conversational speech, and the
other is arranged as a device functioning as a speaker. Thereafter, the output gain adjustment of
the sound to be made to sound to the device which has been made to function as a speaker is
performed (s4). At this time, gain control is performed according to the number of devices that
function as speakers. As described above, the output gain adjustment of each device is performed
so that the overall output gain is constant. Also, the output gain may be increased sequentially
from the listener to the speaker. After adjusting the output gain, speak speech is produced (s5).
[0036]
After the pronunciation, it is determined whether or not the conversation of the same speaker
has ended (s6), and the gain adjustment and the pronunciation are repeated until the
conversation is ended. When it is determined that the conversation has ended, the process is
repeated from speech recognition.
[0037]
As described above, in the in-vehicle conversation assistance device of the present embodiment,
the flat condenser device in which the flat condenser device functioning as a microphone is
previously disposed near the seat and the speech voice is recognized is functioned as a
microphone near the speaker By arranging the device, it is possible to reliably collect
conversational speech. In addition, by arranging a flat condenser device which functions as a
09-05-2019
11
speaker except in the vicinity of the speaker, it is possible to reliably transmit a conversational
voice to a listener. By dynamically changing the arrangement of the device functioning as a
microphone and the device functioning as a speaker according to the positions of the speaker
and the listener, the conversation becomes clear regardless of the position of the occupant. It is
possible to hear.
[0038]
Block diagram showing the construction of a flat type condenser device array of a car equipped
with an in-car conversation aid device Block diagram of an in-car conversation aid device block
diagram of an in-car conversation aid device equipped with a human sensor Flow chart
Explanation of sign
[0039]
1-planar capacitor device 2-control unit 3-voice recognition unit 4-switching control unit 5-gain
adjustment unit 6-motion sensor H-passenger S-seat SW-switch D-device
09-05-2019
12
1/--страниц
Пожаловаться на содержимое документа