close

Вход

Забыли?

вход по аккаунту

?

DESCRIPTION JP2017005369

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 JP2017005369
Abstract: An on-vehicle hands-free call level estimation device that allows a user to know the
degradation level of voice during hands-free call. A vehicle condition acquisition unit acquires a
vehicle condition which is information on a traveling speed, a road surface state, an open / close
state of a window, an air conditioner operating state, an output sound volume of a received voice
set in a speaker, and the like. The hands-free performance estimation unit 32 uses the sound
processed by the hands-free voice processing unit 15 and the vehicle conditions to estimate the
voice deterioration level in the hands-free call. The notification unit 33 notifies the user of the
voice deterioration level estimated by the hands-free performance estimation unit 32. [Selected
figure] Figure 1
In-vehicle hands-free call level estimation device, navigation device, and in-vehicle hands-free
device
[0001]
The present invention relates to an apparatus for notifying a user of the state of hands-free
calling used in a vehicle.
[0002]
In vehicles, there are many opportunities for processing voices, such as voice recognition for the
user to interact with the on-vehicle device, hands-free calling for the user to make a phone call
without any trouble in driving, and the like.
11-04-2019
1
At the time of hands-free calling in the vehicle, not only the voice of the user who is the
transmitter but also the traveling speed, the road surface state, the open / close state of the
window, the air conditioner operating state, the voice of the receiver output from the speaker,
etc. Noise is input to the microphone. Although sound processing or the like for suppressing the
influence of noise is appropriately applied to the sound input to the microphone, there are cases
where it is inevitable that the sound quality reaching the receiver is degraded. However,
conventionally, the user has not been able to know what kind of sound quality of the voice has
finally reached the receiver. That is, even if a voice that is difficult to hear was transmitted, the
user could not notice that unless the receiver pointed out. By the way, even when the user
interacts with the on-vehicle apparatus using voice recognition, the noise input to the
microphone affects the voice recognition rate. In order to inform the user of the influence of
noise, for example, Patent Document 1 discloses a technique of recording background noise
before the user speaks, predicting the performance level of speech recognition based on the
recorded background noise, and notifying the user of it. Have been described. Since hands-free
calling also processes voice as in speech recognition, it is conceivable to estimate the sound
quality heard by the receiver at the time of hands-free calling, for example, using the technique
of Patent Document 1.
[0003]
Japanese Patent Publication No. 2008-501991
[0004]
In speech recognition, it is important to increase the recognition rate, and it is necessary to notify
the user whether speech that can be recognized by the device has been input.
On the other hand, in the hands-free call, it is important to transmit a voice that is easy to hear
and to hear, and it is necessary to notify the user how much of the sense of hearing is on the
other side. Thus, the processing to be evaluated is different between voice recognition and handsfree calling. For example, even a voice with a high recognition rate is not necessarily a voice that
is easy to hear on hearing. Therefore, even if the technology of Patent Document 1 is applied to
hands-free calling, it has not been possible to properly notify the user of the sound quality heard
by the receiver. Also, in a hands-free call, there may be a case in which a reception voice, which is
a voice of a receiver output from the speaker, is input to the microphone. However, since such
received speech does not occur in speech recognition, Patent Document 1 does not consider the
influence of received speech. Also in this respect, it is not appropriate to apply the technique of
11-04-2019
2
Patent Document 1 to hands-free calling.
[0005]
The present invention has been made to solve the above-described problems, and it is an object
of the present invention to provide an on-vehicle hands-free call level estimation device that
allows a user to know the degradation level of voice during hands-free calling. Do.
[0006]
The on-vehicle hands-free call level estimation apparatus according to the present invention
comprises a vehicle condition acquisition unit for acquiring a vehicle condition in which a state of
an element that degrades a voice heard by a receiver during a hands-free call is acquired; A
hands-free performance estimation unit that estimates the degradation level of voice heard by
the receiver during hands-free calling using at least the sound that has been subjected to audio
processing and the vehicle conditions acquired by the vehicle condition acquisition unit; And a
notification unit that outputs the degradation level estimated by the free performance estimation
unit.
[0007]
According to the present invention, the user can know the degradation level of voice during
hands-free calling.
[0008]
It is a figure which shows the structure of the vehicle-mounted hands-free call level estimation
apparatus based on Embodiment 1 of this invention.
It is a figure which shows the example of hardware constitutions of the vehicle-mounted handsfree call level estimation apparatus concerning Embodiment 1 of this invention.
It is a flowchart which shows a process of the vehicle-mounted hands-free call level estimation
apparatus concerning Embodiment 1 of this invention.
[0009]
11-04-2019
3
Embodiment 1
FIG. 1 shows the configuration of an on-vehicle hands-free call level estimation apparatus
according to Embodiment 1 of the present invention. FIG. 1 also shows the on-vehicle hands-free
device 1 and the voice communication device 2. The on-vehicle hands-free device 1 is connected
to a microphone 11 which converts an input voice into an electric signal and outputs the same, a
speaker 12 which outputs the input electric signal as a sound wave, and the microphone 11 and
the speaker 12 to output the electric signal. It has a control unit 13 to process and a voice
communication interface unit 14 for connecting to the voice communication device 2. The
control unit 13 performs various processes on the electric signal output from the microphone 11
and the electric signal output to the speaker 12 using the hands-free speech processing unit 15
and the hands-free speech processing unit 15 for speech processing. And a parameter storage
unit 16 for storing parameters.
[0010]
The voice communication device 2 transmits the voice of the user collected by the microphone
11 and subjected to voice processing by the control unit 13 to the other party who is the receiver
via a communication network (not shown). In many cases, a sound including noise other than the
user's voice is also transmitted. Further, the voice emitted by the receiver is received via a
communication network (not shown) and sent to the on-vehicle hands-free device 1. The voice of
the receiver is then output from the speaker 12. The voice communication device 2 is, for
example, a mobile phone, and is connected to the on-vehicle hands-free device 1, for example,
Bluetooth (registered trademark: hereinafter, the description will be omitted).
[0011]
The on-vehicle hands-free call level estimation device 3 includes a vehicle condition acquisition
unit 31, a hands-free performance estimation unit 32, a notification unit 33, and a deterioration
level improvement unit 34. The vehicle condition acquisition unit 31 acquires vehicle conditions
which are information related to traveling speed, road surface condition, window open / close
condition, air conditioner operating condition, output sound volume of received voice set to the
speaker 12, and the like. These pieces of information are acquired, for example, from a
navigation device (not shown) which is an on-vehicle device connected to the on-vehicle hands-
11-04-2019
4
free call level estimation device 3, or from an ECU (Electronic Control Unit) performing control
on the vehicle body side. To The output sound volume set to the speaker 12 may be acquired
from the on-vehicle hands-free device 1. The acquired vehicle conditions are output to the handsfree performance estimation unit 32 and the deterioration level improvement unit 34. The
vehicle conditions are not limited to the above-described traveling speed and the like, and various
conditions can be considered, as long as the condition of an element that degrades the voice
heard by the receiver during a hands-free call may be indicated.
[0012]
The hands-free performance estimation unit 32 outputs a sound including the user's voice that is
output by the microphone 11 as an electric signal and processed by the hands-free voice
processing unit 15, and a vehicle condition acquired and output by the vehicle condition
acquisition unit 31. And estimate the degradation level of the voice during hands-free calling. The
estimation result is output to the notification unit 33 and the deterioration level improvement
unit 34. The speech degradation level is the degradation level of the user's voice heard by the
receiver. Further, the sound processed by the hands-free speech processing unit 15 used for
estimation of the deterioration level is directly acquired from the hands-free speech processing
unit 15, for example.
[0013]
The notification unit 33 notifies the user of the voice deterioration level by outputting
information on the voice deterioration level estimated by the hands-free performance estimation
unit 32 to an output unit such as a monitor (not shown). The user may be notified by voice via
the speaker 12. The degradation level improvement unit 34 is suitable for being used by the
hands-free voice processing unit 15 using the voice degradation level estimated by the handsfree performance estimation unit 32 and the vehicle condition acquired by the vehicle condition
acquisition unit 31. The parameters are calculated, and the parameters stored in the parameter
storage unit 16 are changed as necessary. Thereby, the audio processing by the hands-free audio
processing unit 15 is changed.
[0014]
As shown in FIG. 2, each unit constituting the on-vehicle hands-free call level estimation device 3
11-04-2019
5
is realized, for example, by the processor 4 executing a program stored in the memory 5. In
addition, multiple processors and multiple memories may be linked and realized. FIG. 1 shows
the case where the in-vehicle hands-free call level estimation device 3 is configured as a device
separate from the in-vehicle hands-free device 1. However, it may be configured integrally with
the on-vehicle hands-free device 1. Further, since the in-vehicle hands-free device 1 is often
configured integrally with a navigation device that performs route guidance and the like, the invehicle hands-free call level estimation device 3 may also be configured integrally with the
navigation device.
[0015]
Next, an example of the process of the on-vehicle hands-free call level estimation apparatus 3
configured as described above will be described using the flowchart shown in FIG. 3. At the time
of hands-free calling, the microphone 11 picks up the voice emitted by the user. At this time,
noises other than the user's voice such as the running noise of the car, the blowing noise of the
air conditioner, and the reception voice are both collected. The hands-free performance
estimation unit 32 acquires from the hands-free speech processing unit 15 a sound collected by
the microphone 11 and subjected to speech processing by the hands-free speech processing unit
15 (step ST1). Subsequently, the vehicle condition acquisition unit 31 acquires a vehicle
condition (step ST2).
[0016]
Subsequently, the hands-free performance estimation unit 32 estimates the voice deterioration
level in the hands-free call using the sound acquired in step ST1 and the vehicle condition
acquired by the vehicle condition acquisition unit 31 (step ST3). ). For estimation of the
deterioration level, an S / N ratio, an evaluation value of speech quality, or the like calculated
using the sound acquired in step ST1 is used. As the S / N ratio is smaller, the degradation level is
estimated to be higher. Also, as an evaluation value of voice quality, for example, a sound quality
evaluation index for an on-vehicle hands-free device formulated by the German Automotive
Industry Association is used. As such a sound quality evaluation index, for example, TMOS (Tosqa
Mean Opinion Score) or the like is available.
[0017]
11-04-2019
6
Vehicle conditions are also used to estimate the degradation level. For example, as the traveling
speed is higher, the deterioration level is estimated to be higher. Further, the degree of
deterioration is estimated to be higher as the unevenness of the road surface condition is more
severe. Also, the larger the window opening, the higher the degradation level is estimated. In
addition, as the output sound volume of the reception voice set to the speaker 12 is larger, the
degradation level is estimated to be higher. Furthermore, the hands-free performance estimation
unit 32 may estimate the deterioration level in the higher direction by using the air volume and
the rainfall information, as the air volume and the rainfall are larger. The air volume and the
rainfall information can be acquired, for example, from an external server (not shown). Also, from
this external server, information capable of estimating the voice degradation level may be
obtained for each traveling point. For example, the S / N ratio for each traveling point, the
evaluation value of voice quality, the radio wave level, and the like. This is, for example, that the S
/ N ratio at each traveling point, the evaluation value of voice quality, the radio wave level and
the like are transmitted to the external server and stored each time the vehicle or another vehicle
travels. If the traveling point of the vehicle is acquired from a navigation device (not shown), the
S / N ratio of the traveling point, the evaluation value of voice quality, the radio wave level and
the like can be searched in the information from the external server. The hands-free performance
estimation unit 32 estimates the degradation level using the search result.
[0018]
As described above, it is possible to estimate the deterioration level from various items such as
the S / N ratio, the traveling speed, and the open / close state of the window. Only one of these
items may be used to estimate the deterioration level, or a plurality of items may be combined to
estimate the deterioration level comprehensively.
[0019]
Subsequently, the notification unit 33 notifies the user of the information on the voice
deterioration level estimated by the hands-free performance estimation unit 32 by screen
display, voice output, and the like (step ST4). For example, the deterioration level is notified by an
index such as high, middle, or low, or the deterioration level is notified by a numerical index such
as a five-step evaluation. This allows the user to know what sound quality of the voice has
reached the receiver. If the receiver is notified that the degradation level of the voice heard by
the receiver is high, the user can take an improvement action such as stopping or closing a
window. Conversely, when notified that the deterioration level is low, the user can safely continue
the hands-free call under the situation as it is.
11-04-2019
7
[0020]
In the flowchart of FIG. 3, processing for improving the deterioration level is continuously shown
after notification of the deterioration level. This will be described below along steps ST5 to ST7.
The degradation level improvement unit 34 uses the voice degradation level estimated by the
hands-free performance estimation unit 32 and the vehicle condition acquired by the vehicle
condition acquisition unit 31 to be appropriately used in the speech processing of the hands-free
speech processing unit 15 The parameter is calculated, and the fact that the parameter can be
changed is output to the notification unit 33 (step ST5). For example, when the output volume of
the receiving voice is high, the value of the echo cancellation parameter capable of appropriately
reducing the echo of the receiving voice is determined. In addition, when the traveling speed is
high, or when the window is widely opened, the value of the noise cancellation parameter
capable of appropriately reducing the noise due to the traveling noise is obtained. Moreover, the
noise due to the air blowing from the air conditioner appears as a sound with a high frequency as
compared to the traveling noise. Therefore, the type of noise whose degradation level is high is
estimated from the vehicle conditions, and the value of the noise cancellation parameter
appropriate for each frequency band is determined.
[0021]
Subsequently, for example, the notification unit 33 causes the monitor integrated with the touch
panel (not shown) to display whether or not the user can select whether or not to change the
parameter of the audio processing, and displays the change of the parameter. It receives (step
ST6). For example, the change execution button and the change unnecessary button are
displayed side by side on the touch panel.
[0022]
If the user selects to change the parameter (step ST6; YES), the deterioration level improvement
unit 34 receives the operation signal from the monitor (not shown) indicating that effect, and
stores the parameter stored in the parameter storage unit 16 , The parameter calculated in step
ST5 is changed (step ST7).
[0023]
On the other hand, when the user selects the change of the parameter as unnecessary (step ST6;
11-04-2019
8
NO), the voice processing is continuously performed with the parameter stored in the parameter
storage unit 16.
[0024]
In step ST5, the deterioration level improving unit 34 identifies an element that raises the
deterioration level out of the vehicle conditions acquired from the vehicle condition acquiring
unit 31, not the parameter calculation, and in the subsequent step ST6, notifies the notification
unit 33. May notify the user of the improvement of the identified main element.
For example, if it is known that the window can be widely opened and the degradation level can
be improved by closing the window, the degradation level improvement unit 34 outputs a
notification to that effect to the notification unit 33.
Then, the notification unit 33 transmits a message indicating that the degradation level is
improved by closing the window, to the user by screen display, voice output, or the like. Thereby,
the user can take an improvement action such as closing a window. Even under the vehicle
condition, the output sound volume of the reception voice set to the speaker 12 may not only be
manually set by the user, but may be automatically set by the deterioration level improvement
unit 34 as with the parameter. Further, in step ST5, the degradation level improving unit 34 may
perform a process of specifying an element that increases the degradation level in combination
with the parameter calculation.
[0025]
Further, in step ST5, the deterioration level improving unit 34 may calculate a plurality of
appropriate parameters. Then, in the subsequent step ST6, the notification unit 33 notifies the
user of a plurality of parameter candidates. As the value of the echo cancellation parameter is
changed in such a direction as to reduce the echo of the received voice, the user's voice heard by
the receiver becomes unnatural. Similarly, as the value of the noise cancellation parameter is
changed in the direction in which noise due to running noise can be reduced, the user's voice
heard by the receiver becomes more unnatural. Since there is such a phenomenon, a plurality of
parameter candidates are notified so that the user can select the balance between the strength of
speech processing performed by the hands-free speech processing unit 15 and the naturalness of
speech. For example, if three candidates are to be notified, parameters with less noise and echo
11-04-2019
9
but with unnatural speech, parameters with more noise and echo with natural but natural speech,
and parameters intermediate between these two are respectively assigned. The button is
displayed so as to be selectable on a touch panel (not shown).
[0026]
Also, when the deterioration level improvement unit 34 identifies an element that clearly
increases the deterioration level based on the vehicle condition, that effect is output to the
notification unit 33, and the notification unit 33 notifies information on the deterioration level.
Instead, it may be notified that the deterioration level is improved if the state of the element is
changed. For example, when the traveling speed is low and the air conditioner is stopped but the
window is widely opened, the degradation level improvement unit 34 immediately notifies the
message that the degradation level is improved if the window is closed. Let me know.
[0027]
If the vehicle condition acquisition unit 31 determines that none of the vehicle conditions is in
the state of increasing the deterioration level, the vehicle conditions are not used for the
subsequent processing, that is, the vehicle condition acquisition unit 31 estimates hands-free
performance. The vehicle conditions may not be output to the unit 32 and the like.
[0028]
Further, the vehicle condition acquisition unit 31 may acquire the vehicle conditions from the
voice communication device 2.
For example, the voice communication device 2 and a navigation device (not shown) are
connected in a communicable state by Bluetooth etc., and the vehicle condition handled by the
navigation device is taken in by the voice communication device 2 and vehicle condition
acquisition from the voice communication device 2 The unit 31 acquires vehicle conditions. In
addition, the navigation device may transmit the vehicle condition to the external server, and the
vehicle condition acquisition unit 31 may acquire the vehicle condition from the external server.
That is, the acquisition route of the vehicle condition can be considered variously. Similarly, the
parameters used by the hands-free voice processing unit 15 are not stored in the parameter
storage unit 16 of the in-vehicle hands-free device 1, but are stored in the voice communication
device 2, and the in-vehicle hands-free call level estimation device 3 and the voice
11-04-2019
10
communication device 2 may be connected in a communicable state by Bluetooth or the like so
that the deterioration level improvement unit 34 can make changes.
[0029]
In addition, the degradation level improvement unit 34 automatically does not select whether the
user changes the parameters used by the handsfree voice processing unit 15 or the output sound
volume of the reception voice set in the speaker 12 or not. A process of changing these settings
may be performed.
[0030]
As described above, according to the on-vehicle hands-free call level estimation device according
to the first embodiment, the sound obtained by the microphone 11 being sounded and subjected
to the voice processing by the hands-free voice processing unit 15 and the vehicle condition
acquisition unit The hands-free performance estimation unit 32 estimates the degradation level
of the voice during the hands-free call, using the vehicle conditions acquired by the V.31.
Then, the notification unit 33 notifies the user of the deterioration level estimated by the handsfree performance estimation unit 32. Thereby, the user can know the degradation level of the
voice in the hands-free call.
[0031]
The deterioration level improving unit 34 calculates a parameter suitable for use in speech
processing using the deterioration level estimated by the hands-free performance estimation unit
32 and the vehicle condition acquired by the vehicle condition acquisition unit 31. I decided.
Therefore, it is possible to perform appropriate audio processing depending on the situation.
[0032]
Further, the notification unit 33 can selectably output the change necessity of the parameter
used in the speech processing, and when the user selects the change necessity, the deterioration
level improvement unit 34 calculates the parameter used in the speech processing. It was
11-04-2019
11
decided to change to the parameter. Therefore, the user can easily make the listener hear the
voice with a low degradation level as needed.
[0033]
In addition, the vehicle condition acquiring unit 31 includes the deterioration level improving
unit 34 that outputs information indicating an action that can improve the deterioration level to
the notifying unit 33 using the vehicle conditions acquired. Therefore, even if there is a limit to
the improvement of the degradation level only by speech processing, the improvement of the
degradation level is expected.
[0034]
Further, the deterioration level improving unit 34 calculates a plurality of parameters suitable for
being used in the audio processing. Therefore, the user can appropriately select the state of the
voice heard by the receiver.
[0035]
In the present invention, within the scope of the invention, modifications of optional components
of the embodiment or omission of optional components of the embodiment is possible.
[0036]
Reference Signs List 1 in-vehicle hands-free device, 2 voice communication device, 3 in-vehicle
hands-free call level estimation device, 4 processors, 5 memories, 11 microphones, 12 speakers,
13 control units, 14 voice communication interface units, 15 hands-free voice processing units,
16 Parameter storage unit, 31 vehicle condition acquisition unit, 32 hands-free performance
estimation unit, 33 notification unit, 34 degradation level improvement unit.
11-04-2019
12
Документ
Категория
Без категории
Просмотров
0
Размер файла
23 Кб
Теги
description, jp2017005369
1/--страниц
Пожаловаться на содержимое документа