CN108674344B

CN108674344B - Voice processing system based on steering wheel and application thereof

Info

Publication number: CN108674344B
Application number: CN201810293747.9A
Authority: CN
Inventors: 杨度; 沈寅
Original assignee: Zebred Network Technology Co Ltd
Current assignee: Zebred Network Technology Co Ltd
Priority date: 2018-03-30
Filing date: 2018-03-30
Publication date: 2024-04-02
Anticipated expiration: 2038-03-30
Also published as: CN108674344A

Abstract

The invention discloses a voice processing system based on a steering wheel and application thereof, comprising a collecting unit, a processing unit and an output unit, wherein the collecting unit comprises two sound pickup units, at least one sound pickup unit is arranged on a middle control screen of a vehicle or is adjacently arranged on the middle control screen and used for collecting a first voice command, the other sound pickup units are arranged on the steering wheel of the vehicle and used for collecting a second voice command, the processing unit is communicatively connected with the two sound pickup units, and the processing unit generates an optimized control command by comparing the first voice command with the second voice command, and the output unit is communicatively connected with the processing unit, wherein the output unit is used for outputting the control command.

Description

Voice processing system based on steering wheel and application thereof

Technical Field

The invention relates to the field of vehicle voice control, in particular to a voice processing system based on a steering wheel and application thereof.

Background

With the development of technology, more and more technological achievements gradually go out of the laboratory and into our lives, and an on-board voice control system is one of the technologies. The vehicle-mounted voice control system is widely applied to vehicles to allow a user to control the vehicles in a voice control mode, namely, the user can control the vehicles only by emitting specific sounds, so that the vehicle can complete specific functions without specific actions of the user, the control of the vehicle by a driver of the vehicle is greatly facilitated, and the safety of the driving process is ensured.

For example, when a driver of a vehicle wants to open a window, the driver needs to touch a window control button to control opening and closing of the window. However, with the application of the vehicle voice control system, a vehicle driver only needs to send out a voice command for opening the vehicle window, and the vehicle voice control system can correspondingly control the vehicle window according to the voice command without touching a vehicle window control button by a user, so that the vehicle driver can conveniently control the vehicle.

On the other hand, vehicle drivers are a recognized and relatively boring task, and during long driving, drivers often prefer to play some music, thereby increasing the enjoyment of the vehicle during driving. If a driver of a vehicle wants to play music while the vehicle is traveling, the driver of the vehicle conventionally touches a switch of a vehicle-mounted player on the vehicle to turn on the vehicle-mounted player to play music. When a driver touches the vehicle-mounted player switch, the driver's sight is inevitably separated from the running direction of the vehicle for finding the position of the vehicle-mounted player switch, and in the process, if an emergency occurs on the running route of the vehicle, the driver of the vehicle is difficult to timely and effectively react, so that the probability of accident occurrence is greatly increased.

Through the vehicle-mounted voice control system, a vehicle driver can not need to directly touch a switch of the vehicle-mounted player when the vehicle driver wants to play music in the driving process, and only needs to send out a voice control instruction, the vehicle-mounted voice control system can open the vehicle-mounted player to play music according to the voice control instruction, so that the limitation of the traditional vehicle-mounted player to the vehicle driver is greatly liberated, the vehicle driver can concentrate on the driving of the vehicle, the probability of accident occurrence is reduced, and the safety performance of the vehicle is improved.

However, the conventional vehicle voice control system has a great limitation in that the sound receiving device (the device for receiving the voice of the user) of the conventional vehicle voice control system is usually disposed near the central control panel of the vehicle, and when the external environment and/or the internal environment of the vehicle are relatively noisy, the sound receiving device disposed near the central control panel of the vehicle is difficult to accurately receive the corresponding voice command in the noisy environment, so that the vehicle voice control system cannot generate the corresponding motion information or may generate the wrong motion information according to the voice command, which greatly affects the control capability of people on the vehicle, and greatly discounts the driving experience of the vehicle.

For example, when a vehicle driver sends out a voice command to play music in the process of driving the vehicle, but when more people are in the vehicle and the environment in the vehicle is noisy, the voice sent by other people in the vehicle will interfere with the vehicle voice control system, so that the vehicle voice control system cannot quickly recognize the voice command sent by the vehicle driver in the noisy environment and cannot timely and effectively respond according to the voice command of the driver.

In addition, the vehicle voice control system may recognize the wrong voice command in a noisy environment and generate wrong action information according to the recognized wrong voice command, for example, the vehicle voice control system may recognize the voice command for playing music as a voice command for opening a vehicle door in a noisy environment, and the vehicle door of the vehicle is opened in the driving process of the vehicle, which causes a great potential safety hazard to the driving process of the vehicle. In particular in noisy environments, echoes are present.

The radio device of the traditional vehicle-mounted voice control system is arranged on the middle control screen of the vehicle, so that a vehicle driver can sound close to the middle control screen of the vehicle to obtain a good radio effect, the use is very inconvenient, and potential safety hazards exist. In addition, the sound receiving device arranged on the middle control screen is small in loudness when receiving voice instructions sent by a driver when the voice instructions reach the vicinity of the middle control screen of the vehicle, particularly when the driver drives the vehicle, the driver often needs to rotate the face left and right, particularly the face often needs to be offset in the opposite direction of the middle control screen, at the moment, the vehicle-mounted sound receiving device often cannot accurately and rapidly pick up the voice instructions, and corresponding actions cannot be generated according to the voice instructions.

Therefore, how to further improve the speech recognition efficiency of the vehicle speech control system becomes a key problem to be solved in future development of the vehicle speech control system.

Disclosure of Invention

It is an object of the present invention to provide a steering wheel based speech processing system and application thereof, wherein at least one speech command issued by a driver can be processed by the steering wheel based speech processing system, so that the finally formed speech is more accurate.

Another object of the present invention is to provide a steering wheel-based speech processing system and a processing method thereof, which, in comparison with a conventional vehicle-mounted speech processing system, pick up at least two speech commands, wherein one of the speech commands is sent by a driver collected based on a sound receiving device provided on the steering wheel, so as to effectively identify that the driver repeatedly sends out speech commands.

Another object of the present invention is to provide a steering wheel-based speech processing system and a processing method thereof, which have higher definition and can accurately obtain a speech instruction issued by a driver in a relatively noisy environment, compared with a conventional vehicle-mounted speech processing system.

Another object of the present invention is to provide a steering wheel-based speech processing system and a processing method thereof, which can accurately obtain a speech command sent by a driver even in the presence of an echo, as compared with a conventional vehicle-mounted speech processing system.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, wherein the voice processing system includes at least one first sound pickup unit and at least one second sound pickup unit, and the first sound pickup unit and the second sound pickup unit are respectively disposed on a central control panel of a vehicle and a steering wheel of the vehicle, and the first sound pickup unit and the second sound pickup unit cooperate to generate more accurate voice commands by comparing the voice commands picked up by the first sound pickup unit and the second sound pickup unit.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, wherein a first voice command collected by the first sound pickup unit and a second voice command collected by the second sound pickup unit can be mutually corrected, so as to improve accuracy and efficiency of recognizing the voice command by the voice processing system.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, wherein one of the first sound pickup unit and the second sound pickup unit is a main sound pickup unit, and the other sound pickup unit is an auxiliary sound pickup unit, and a voice command collected by the auxiliary sound pickup unit can be used for correcting the voice command collected by the main sound pickup unit, so that accuracy and efficiency of the voice processing system for recognizing the voice command are improved.

It is another object of the present invention to provide a steering wheel based speech processing system and a processing method thereof, wherein the first sound pickup unit and the second sound pickup unit are each capable of switching between a main sound pickup unit and a sub sound pickup unit.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, wherein the first sound pickup unit and the second sound pickup unit form a sound field, and when a voice command sent by a driver is transmitted to the sound field, the voice command can be collected by the first sound pickup unit and the second sound pickup unit.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, in which the second sound pickup unit is adjustably disposed on a steering wheel of the vehicle, for example, the direction of the second sound pickup unit can be adjusted along with the change of the face direction of the driver, so that the second sound pickup unit can collect voice commands with better effect, so as to improve the accuracy and efficiency of recognizing voice commands by the voice processing system.

Another object of the present invention is to provide a steering wheel-based voice processing system and a processing method thereof, wherein the second sound pickup unit is adjustably disposed on a steering wheel of the vehicle, so that the sound pickup field formed by the first sound pickup unit and the second sound pickup unit is a dynamic sound pickup field.

To achieve at least one of the above objects, the present invention provides a steering wheel based speech processing system comprising:

the collecting unit comprises two sound pickup units, wherein at least one sound pickup unit is arranged on a middle control screen of a vehicle or is adjacently arranged on the middle control screen and used for collecting a first voice instruction, and the other sound pickup units are arranged on a steering wheel of the vehicle and used for collecting a second voice instruction;

a processing unit, wherein the processing unit is communicatively connected to both of the pickup units, and the processing unit generates a control instruction that is optimized by comparing the first voice instruction and the second voice instruction; and

An output unit, wherein the output unit is communicatively coupled to the processing unit, wherein the output unit is configured to output the control instruction.

According to an embodiment of the present invention, the sound pickup unit disposed on the middle control panel of the vehicle or disposed adjacent to the middle control panel is a first sound pickup unit, the sound pickup unit disposed on the steering wheel is a second sound pickup unit, wherein the first sound pickup unit is configured to collect a first voice command, and the second sound pickup unit is configured to collect a second voice command, wherein the processing unit compares a sound quality of the first voice command and a sound quality of the second voice command, so as to generate the control command according to a voice command with a better sound quality of one of the first voice command and the second voice command, so as to control the vehicle.

According to an embodiment of the present invention, the sound pickup unit disposed on the middle control panel of the vehicle or disposed adjacent to the middle control panel is a first sound pickup unit, the sound pickup unit disposed on the steering wheel is a second sound pickup unit, wherein the first sound pickup unit is configured to collect a first voice command, and the second sound pickup unit is configured to collect a second voice command, and the processing unit superimposes the first voice command and the second voice command to generate the control command for controlling the vehicle.

According to an embodiment of the present invention, the sound pickup unit disposed on the middle control panel of the vehicle or disposed adjacent to the middle control panel is a first sound pickup unit, the sound pickup unit disposed on the steering wheel is a second sound pickup unit, wherein the first sound pickup unit is configured to collect a first voice command, and the second sound pickup unit is configured to collect a second voice command, and the processing unit performs difference processing on the first voice command and the second voice command to generate the control command for controlling the vehicle.

According to an embodiment of the present invention, the sound pickup unit disposed on the middle control panel of the vehicle or disposed adjacent to the middle control panel is a first sound pickup unit, the sound pickup unit disposed on the steering wheel is a second sound pickup unit, wherein the first sound pickup unit is configured to collect a first voice command, and the second sound pickup unit is configured to collect a second voice command, wherein the processing unit is configured to intercept a better-quality segment in the first voice command and a better-quality segment in the second voice command to generate the control command, so as to control the vehicle.

According to an embodiment of the present invention, the control unit compares the first voice command with the second voice command according to the following conditions: the sound size, the frequency of the sound, the background sound size.

To achieve at least one of the above objects, the present invention provides a voice control system, wherein the voice control system comprises:

a speech processing system according to any of the above; and

a control unit, wherein the control unit is communicatively connected to the output unit, wherein the control unit executes the control instructions output by the output unit to control the vehicle.

To achieve at least one of the above objects of the present invention, the present invention provides a steering wheel-based voice processing method, the voice processing method comprising the steps of:

(a) Forming a sound pickup field in a riding space of a vehicle by arranging at least one first sound pickup unit in a middle control panel of the vehicle or in the vicinity of the middle control panel and at least one second sound pickup unit in at least one steering wheel of the vehicle;

(b) Collecting a first voice command and a second voice command collected by the first pickup unit and the second pickup unit respectively;

(c) Generating a control instruction by comparing and optimizing the first voice instruction and the second voice instruction; and

(d) And outputting the control instruction.

According to an embodiment of the present invention, in the step (a), the second sound pickup unit is adjustably disposed on the steering wheel, so that the sound pickup field formed by the first sound pickup unit and the second sound pickup unit is a dynamic sound pickup field.

According to an embodiment of the present invention, in the step (a), at least one third pickup unit is disposed on at least one steering wheel, so as to form the sound field by using the third pickup unit and the second pickup unit.

According to an embodiment of the present invention, in the above method, the second sound pickup unit is adjustably disposed on the steering wheel, so that the sound pickup field formed by the second sound pickup unit and the third sound pickup unit is a dynamic sound pickup field.

According to an embodiment of the present invention, in the above method, the third sound pickup unit is adjustably disposed on the steering wheel, so that the sound pickup field formed by the second sound pickup unit and the third sound pickup unit is a dynamic sound pickup field.

According to an embodiment of the present invention, in the above method, the third sound pickup unit is adjustably disposed on the steering wheel, so that the sound pickup field formed by the second sound pickup unit and the third sound pickup unit is the dynamic sound pickup field.

According to an embodiment of the present invention, in the step (c), the method further includes the steps of: and comparing the sound quality of a first voice command acquired by the first sound pickup unit with the sound quality of a second voice command acquired by the second sound pickup unit, and generating the control command according to one voice command with better sound quality in the first voice command and the second voice command so as to control the vehicle.

According to an embodiment of the present invention, in the step (c), the method further includes the steps of: and superposing a first voice command acquired by the first sound pickup unit and a second voice command acquired by the second sound pickup unit to generate the control command for controlling the vehicle.

According to an embodiment of the present invention, in the step (c), the method further includes the steps of: the difference set processes a first voice command acquired by the first pickup unit and a second voice command acquired by the second pickup unit to generate the control command for controlling the vehicle.

According to an embodiment of the present invention, in the step (c), the method further includes the steps of: and intercepting the fragment with better sound quality in the first voice command and the fragment with better sound quality in the second voice command to generate the control command for controlling the vehicle.

To achieve at least one of the above objects, the present invention provides a method of steering wheel based voice control, wherein the method comprises:

generating a control instruction according to any one of the above-mentioned voice processing methods; and

and controlling the vehicle by executing the control instruction.

the collecting unit comprises two sound pickup units, wherein the two collecting units are respectively arranged on the steering wheel, and the two sound pickup units respectively collect a first voice instruction and a second voice instruction;

According to an embodiment of the invention, at least one of the sound pickup units is provided at a center portion of the steering wheel.

Drawings

FIG. 1A shows a schematic view of a steering wheel radio-enabled vehicle of the present invention.

FIG. 1B shows a partial schematic view of a steering wheel radio-enabled vehicle of the present invention.

Fig. 2A shows a schematic view of a steering wheel of a vehicle according to the present invention in a state in which the steering wheel is turned.

Fig. 2B shows a schematic view of a steering wheel of a vehicle according to the present invention in another state after the steering wheel is turned.

Fig. 3 shows a partial schematic view of a steering wheel radio-enabled vehicle in accordance with another embodiment of the present invention.

Fig. 4 shows a schematic diagram of a steering wheel based speech processing system and a speech control system according to an embodiment of the invention.

Fig. 5 illustrates a method of steering wheel based speech processing in accordance with one embodiment of the present invention.

Fig. 6 shows a schematic diagram of a steering wheel based speech processing system and a speech control system according to another embodiment of the invention.

Fig. 7 illustrates a steering wheel based speech processing method according to another embodiment of the present invention.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.

It will be appreciated by those skilled in the art that in the present disclosure, the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," etc. refer to an orientation or positional relationship based on that shown in the drawings, which is merely for convenience of description and to simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore the above terms should not be construed as limiting the present invention.

It will be understood that the terms "a" and "an" should be interpreted as referring to "at least one" or "one or more," i.e., in one embodiment, the number of elements may be one, while in another embodiment, the number of elements may be plural, and the term "a" should not be interpreted as limiting the number.

Referring to fig. 1A-7 of the drawings, a steering wheel based speech processing system 100 in accordance with a preferred embodiment of the present invention is disclosed and described in the following description, wherein the speech processing system 100 is adapted for use with at least one vehicle 200 for receiving and processing at least one speech command issued by a driver of the vehicle 200 to form a control command based on which the vehicle 200 is thereby speech controlled.

The vehicle 200 includes a vehicle body 201, a steering wheel 202, and a center control panel 203, wherein the steering wheel 202 and the center control panel 203 are respectively provided to the vehicle body 201, and the steering wheel 202 and the center control panel 203 are both located in a seating space of the vehicle 200, the steering wheel 202 allows a driver to operate to control the vehicle 200, for example, the driver can drive the vehicle 200 by operating the steering wheel 202, or the driver can operate the vehicle 200 by controlling the steering wheel 202, and the center control panel 203 allows a user to view and control a state of the vehicle 200. Compared with the traditional vehicle, the invention receives the voice command in a mode of approaching the position of the voice command sender by arranging the sound receiving device at the position of the steering wheel 202 of the vehicle 200, thereby improving the efficiency, accuracy and success rate of the voice command being identified. For example, when the driver faces the steering wheel 202 of the vehicle 200, the mouth of the driver approaches the sound receiving device provided to the steering wheel 202, so that when the driver gives the voice command, the sound receiving device provided to the steering wheel 202 can receive the voice command at a position close to the mouth of the driver, thereby being beneficial to improving the efficiency and success rate of recognizing the voice command.

Further, the steering wheel 202 includes a peripheral portion 2021, an inner portion 2022, and a central portion 2023, wherein the peripheral portion 2021 and the central portion 2023 are respectively connected to the inner portion 2022.

In one embodiment of the present invention, at least two sound receiving devices 80 are provided on the steering wheel 202 to collect the voice command from the driver near the steering wheel 202. For example, in one embodiment of the present invention, at least one of the sound pickup devices 80 is disposed on the center portion 2023, at least one of the sound pickup devices 80 is disposed on the inner portion 2022, wherein two of the sound pickup devices 80 can cooperate with each other to form a sound pickup field at a position of the inner portion of the vehicle body 201 near the steering wheel 202 for collecting the voice command issued by the driver, and in this embodiment, no matter in which direction the steering wheel 202 is rotated, the position of the sound pickup device 80 disposed on the center portion 2023 relative to the driver does not change, so that the sound pickup device 80 disposed on the center portion 2023 can collect the user command issued by the driver better whenever the driver faces forward all the time while driving the vehicle. While those skilled in the art will appreciate that the driver's face is directed toward the center portion 2023 most of the time. In another embodiment of the present invention, at least two of the sound-receiving devices 80 are symmetrically disposed on the circumferential portion 2021 or the inner portion 2022, as shown in fig. 3, two of the sound-receiving devices 80 are symmetrically disposed on the steering wheel 202, in such a way that the sound-receiving field 500 formed by the two sound-receiving devices 80 presents a dynamically changing turntable, so as to better collect the voice command issued by the driver when the posture of the user changes with the operation of the steering wheel 202.

In another embodiment of the present invention, at least one of the sound-receiving devices 80 is disposed on the middle control panel 203, at least one of the sound-receiving devices 80 is disposed on the steering wheel 202, wherein the sound-receiving device 80 disposed on the middle control panel 203 and the sound-receiving device 80 disposed on the steering wheel 202 can cooperate with each other to form the sound-receiving field inside the vehicle body 201 for collecting the voice command issued by the driver.

In the following description, for convenience of explanation and understanding of the contents and features of the vehicle of the present invention, the sound pickup device 80 provided to the center control panel 203 is defined as a first sound pickup device 80a, the sound pickup device 80 provided to the center portion of the steering wheel 202 is defined as a second sound pickup device 80b, wherein the sound pickup device 80 provided to the inside turn portion 2022 is defined as a third sound pickup device 80c, and wherein at least two of the first sound pickup device 80a provided to the center control panel 203 and the second sound pickup device 80b and the third sound pickup device 80c provided to the steering wheel 202 are capable of forming the sound pickup field inside the vehicle body 201.

Preferably, the inner portion 2022 of the steering wheel 202 is further provided with a third sound-receiving device 80c, wherein the third sound-receiving device 80c is disposed on the inner portion 2022 of the steering wheel 202, and wherein the inner portion 2022 is rotated when the steering wheel 202 is operated by a user, so that the sound-receiving field 500 is formed as a dynamic sound-receiving field. For example, as shown in fig. 2A, when the driver turns the steering wheel 202 to the left, the face of the driver also turns to the left, and at this time, the third sound receiving device 80c can collect the voice instruction sent by the user better because the third sound receiving device 80c disposed on the steering wheel 202 can be turned correspondingly and is close to the face of the driver. For example, as shown in fig. 2B, when the driver turns the steering wheel 202 to the right, the face of the driver also turns to the right, and at this time, the third sound receiving device 80c disposed on the steering wheel 202 can be correspondingly turned and approach to the face of the driver, so that the third sound receiving device 80c can better collect the voice command sent by the user. In this way, the sound-receiving field 500 defined by the third sound-receiving device 80c and the selected first sound-receiving device 80a and the second sound-receiving device 80c is adjusted to better collect the voice command issued by the driver during the user's operation of the steering wheel 202.

It should be noted that, in the present invention, the first sound receiving device 80a provided on the central control panel 203 and the second sound receiving device 80b provided on the steering wheel 202 are only for distinguishing the position of each sound receiving device 80, and the feature of each sound receiving device 80 is not limited. In addition, in the vehicle of the present invention, the type of the sound receiving apparatus 80 does not constitute a limitation on the content and the range of the vehicle of the present invention, wherein the sound receiving apparatus 80 may be capable of receiving sound.

In addition, the first sound-receiving device 80a and the second sound-receiving device 80b are both directly exposed to the interior of the vehicle main body 201, and in other possible examples of the vehicle of the present invention, the first sound-receiving device 80a and the second sound-receiving device 80b may be hidden as long as the sound-receiving device 80 can normally collect sound transmitted to the sound-receiving field, for example, the second sound-receiving device 80b provided to the steering wheel 202 may be hidden in the interior of the steering wheel 202 and communicate with the outside through one or more air holes, so that when the sound propagates to the sound-receiving field, the sound can be collected by the second sound-receiving device 80b through the air holes.

In addition, one of the first sound receiving device 80a and the second sound receiving device 80b is a main sound receiving device, the other sound receiving device is an auxiliary sound receiving device, and the first sound receiving device 80a and the second sound receiving device 80b can be switched between the main sound receiving device and the auxiliary sound receiving device along with the change of the gesture of facing the driver. Preferably, the first sound pickup device 80a and the second sound pickup device 80b are capable of switching between a primary sound pickup device and a secondary sound pickup device depending on a distance between the driver facing the sound pickup device. For example, when the driver is closer to the first sound pickup device 80a, the first sound pickup device 80a may be a primary sound pickup device and the second sound pickup device 80b may be a secondary sound pickup device; when the driver is closer to the second sound pickup device 80b, the first sound pickup device 80a may be a secondary sound pickup device, and the second sound pickup device 80b may be a primary sound pickup device. Optionally, the first sound pickup device 80a and the second sound pickup device 80b can switch between the primary sound pickup device and the secondary sound pickup device depending on the face orientation of the driver. For example, when the face of the user faces the first sound pickup device 80a or is close to the first sound pickup device 80a, the first sound pickup device 80a is a main sound pickup unit, and the second sound pickup device 80b is an auxiliary sound pickup device; when the face facing the driver faces the second sound pickup device 80b or is close to the second sound pickup device 80b, the second sound pickup device 80b is the main sound pickup unit 12, and the first sound pickup device 80a is the auxiliary sound pickup device.

It should be noted that, in the embodiment of the present invention, the primary sound receiving device is used to collect the voice command sent by the driver, and the secondary sound receiving device is used to collect the voice command sent by the driver and the background sound except for the voice command sent by the driver.

It is further noted that in the present invention, the second sound receiving device 80b and the third sound receiving device 80c disposed on the reversing disc 202 may be simultaneously used as the main sound receiving device to collect the voice command of the driver, wherein the first sound receiving device 80c may be disposed away from the driver to collect the background sound.

In a specific example of the vehicle of the invention, the vehicle further comprises a control device 300 and a detection device 400 communicatively connected to the control device 300, wherein the control device 300 and the detection device 400 are respectively arranged to the vehicle body 201, wherein each of the sound receiving devices 80 in the sound receiving field 500 is respectively controllably connected to the control device 300. In other words, in the specific example of the vehicle shown in the drawings, the first sound receiving device 80a and the second sound receiving device 80b are each controllably connected to the control device 300.

The control device 300 comprises a processor 3001 and a controller 3002, wherein each of the sound pickup devices 80 in the sound pickup field 500 is controllably connected to the controller 3002, respectively, wherein the processor 3001 is connected to the detecting device 400 and the controller 3002, respectively, to drive the controller 3002 to adjust the sound pickup field 500 formed by the sound pickup devices 80 near the steering wheel 202 according to the posture of the driver detected by the detecting device 400 at the processor 3001, so as to better collect the voice command issued by the user.

It is to be noted that the position where the processor 3001 is provided to the vehicle body 201 is not limited in the vehicle of the invention. In addition, the type of the control device 300 is not limited in the vehicle of the present invention, as long as it can calculate and process data. For example, the control device 300 may be implemented as, but is not limited to, a CPU.

It is also worth mentioning that the detection device 400 may be a camera, a microwave detector, an ultrasonic detector, or the like for detecting the posture of the user, wherein the position where the detection device 400 is provided to the vehicle body 100 is determined according to the type of the detection device 400. For example, when the detection device 400 is implemented as a camera, the detection device 400 may be provided at a front windshield of the vehicle body 201, or the detection device 400 may be provided at the center control panel 203; when the detecting device 400 is implemented as a microwave detector, the detecting device 400 may be provided at the center control panel 203, or the detecting device 400 may be provided at the roof of the vehicle body 201.

In another specific example of the vehicle of the present invention, the control device 300 includes a communication device 3003 and the controller 3002, wherein each of the detection device 400 and the sound reception device 80 in the sound reception field 500 is respectively communicatively connected to the controller 3002, wherein the communication device 3003 can be communicatively connected to a cloud server 700, wherein data obtained by the detection device 400 by detecting the posture of the user can be uploaded to the cloud server 700 through the communication device 3003 to be calculated and processed at the cloud server 700, and then, instructions generated by the cloud server 700 can be further transmitted to the controller 3002 through the communication device 3003. That is, the processor 3001 may not be configured on the vehicle on which the communication device 3003 is configured. However, it is a preferable scheme to configure the controller 3002 and the communication device 3003 on the vehicle at the same time.

It is to be noted that the position where the communication device 3003 is provided to the vehicle body 100 is not limited in the vehicle of the invention. In addition, the type of the communication device 3003 is not limited in the vehicle of the invention, as long as it can realize transmission of data.

Further, the sound receiving device 80 includes a seat 81 and at least one sound receiving main body 82, wherein the sound receiving main body 82 is drivably disposed on the seat 81, and the seat 81 is disposed on the vehicle body 201. For example, in the preferred example of the vehicle shown in fig. 1, the adjusting seat 81 of the sound receiving device 80 may be provided to the middle control panel 203 and the steering wheel 202. The adjusting seat 81 can drive the sound receiving main body 82 to rotate so as to adjust the direction of the sound receiving main body 82, that is, after the direction of the sound receiving main body 82 is driven by the adjusting seat 81 to be changed, the direction of the sound receiving device 10 is also changed. That is, in this particular example of the vehicle of the present invention, the orientation of the sound receiving body 82 is defined as the orientation of the sound receiving device 10. It should be noted that, the manner in which the adjusting seat 81 drives the sound-receiving main body 82 to rotate is not limited in the vehicle of the present invention, for example, the adjusting seat 81 can drive the sound-receiving main body 82 to swing left and right or up and down along a preset direction, or the adjusting seat 81 can drive the sound-receiving main body 82 to rotate in the full circumferential direction. Preferably, the adjusting seat 81 may be implemented as a motor or a structure with a motor, wherein the adjusting seat 81 can be rotated to rotate the sound receiving body 82 when receiving a command.

In a specific example of the vehicle of the present invention, the adjustment seat 81 is controllably connected to the controller 3002 of the control device 300, so that the adjustment seat 81 can be rotated to rotate the sound receiving body 82 when receiving an instruction generated by the control device 300. In another specific example of the vehicle of the present invention, the docking station 81 is communicatively connected to the communication device 3003, so that the docking station 81 can rotate to rotate the sound receiving body 82 when receiving the instruction generated by the cloud server 700 through the communication device 500.

More preferably, the vehicle 200 further comprises a voice quality optimizing device 90, wherein the voice quality optimizing device 90 is connected to the first sound receiving device 80a and the second sound receiving device 80b, and the voice quality optimizing device 90 can compare the voice command collected by the first sound receiving device 80a and the second sound receiving device 80b to form the voice command with better voice quality.

A preferred embodiment of the speech processing system 100 provided by the present invention is further described in the following description, wherein the speech processing system 100 comprises a collecting unit 10, a processing unit 20 and an output unit 30, the collecting unit 10, the processing unit 20 and the output unit 30 are communicatively connected to each other, wherein the collecting unit 10 is configured to collect the speech command and send the speech command to the processing unit 20, and the processing unit 20 processes the speech command collected by the collecting unit 10 and forms a control command to enable to improve the accuracy of the driver's speech control of the vehicle 200.

The collection unit 10 further includes at least one first sound pickup unit 11 and at least one second sound pickup unit 12, wherein the first sound pickup unit 11 and the second sound pickup unit 12 are respectively integrated with the middle control panel 203 of the vehicle 200 or the first sound pickup device 80a disposed at a position near the middle control panel 203 and the second sound pickup device 80b of the steering wheel 202 of the vehicle 200, and when a driver of the vehicle gives out the voice command desired to control the vehicle 200 in the vehicle, the first sound pickup unit 11 and the second sound pickup unit 12 work cooperatively to complete collection of the voice command. That is, when the voice command is issued by the driver of the riding space of the vehicle 200, the second sound pickup unit 12 provided in the middle control panel 203 or in the vicinity of the middle control panel 203 and the second sound pickup unit 80b provided in the steering wheel 202 can both pick up the voice command issued by the user. Subsequently, the voice command collected by the first sound pickup unit 11 and the voice command collected by the second sound pickup unit 12 can be mutually corrected by a user, so as to improve the efficiency and accuracy of recognizing the voice command by the voice processing system 100, thereby improving the user experience of the user and ensuring the safety of the driving process.

Referring to fig. 1A to 3, the first sound pickup unit 11 and the second sound pickup unit 12 can cooperate with each other to be able to collect the voice command in the sound pickup field 500, wherein when a driver located in a seating space of the vehicle 200 issues the voice command and the voice command is transmitted to the sound pickup field 500, the voice command can be collected by the first sound pickup device 80a and the second sound pickup device 80b forming the sound pickup field 500, wherein the first sound pickup unit 11 and the second sound pickup unit 12 integrated in the first sound pickup device 80a and the second sound pickup device 80b can collect the voice command collected by the first sound pickup device 80a and the second sound pickup device 80b, respectively. The radio field 500 is a dynamic radio field in the present invention, wherein the state of the radio field 500 can be changed with the change of the posture of the driver. Specifically, the direction of the second sound pickup device 80b may be adjusted, for example, the direction of the second sound pickup device 80b may be always directed toward the face of the driver, so that the sound pickup field 500 formed by the first sound pickup device 80a and the second sound pickup device 80b is a dynamic sound pickup field, and thus the voice commands collected by the first sound pickup unit 11 and the second sound pickup unit 12 are in different states in the sound pickup field 500.

The processing device 20 is capable of processing the voice command collected by the first sound pickup unit 11 and the second sound pickup unit 12 to form the control command.

In the voice processing system 100 of the present invention, by providing the second sound pickup unit 12 to the second sound receiving device 80b of the steering wheel 202 of the vehicle 200, when the driver of the riding space of the vehicle 200 issues the voice command, the second sound pickup unit 12 of the collection unit 10 can accurately collect the voice command issued by the voice command issuer from the second sound receiving device 80a because the second sound pickup unit 12 is close to the position of the driver of the voice command issuer.

For example, when the driver gives the voice command, the second sound receiving device 121 provided to the steering wheel 202 can collect the voice command at a position close to the driver, and at the same time, the first sound pickup unit 11 provided near the center control panel 203 of the vehicle 200 can collect the voice command given by the driver. Preferably, the direction of the second sound receiving device 80b is adjustable, that is, the second sound receiving device 80b is adjustably disposed on the steering wheel 202, so that when the direction of the face of the driver changes, the direction of the second sound pickup unit 12 for collecting the voice command can be adjusted, so that the second sound pickup unit 12 can always face the face of the driver or approach to face the face of the driver, so as to collect the voice command issued by the driver.

In addition, when the driver sitting in the rear row of the vehicle 200 issues the voice command, the first pickup unit 11 is located at the position of the middle control panel 203, which is relatively far away from the steering wheel 202, close to the position where the driver issues the voice command, and the first pickup unit 11 can well collect the voice command issued by the rear row driver of the vehicle 200.

The second sound pickup unit 12 is arranged on the second sound pickup device 80b at the position of the steering wheel 202 of the vehicle 200, and sound pickup is performed by approaching to the position where the voice command is sent, so that the problem that the traditional vehicle-mounted voice processing system only sets the sound pickup device near the control screen in the vehicle to have difficulty in picking up sound is well solved, and the problem of inaccurate sound pickup is favorable for improving the recognized efficiency and accuracy of the voice command.

And, the first sound pickup unit 11 and the second sound pickup unit 12 form the sound pickup field 500 between the steering wheel 202 and the middle control panel 203 of the vehicle 200, when a driver sits in the riding space of the vehicle 200 to control the steering wheel 202, the driver is in the sound pickup field 500 formed by the first sound pickup unit 11 and the second sound pickup unit 12, and the voice command sent by the driver can be well collected by the first sound pickup unit 11 and the second sound pickup unit 12 of the collecting unit 10 in the sound pickup field 500.

Still further, the processing unit 20 includes a voice receiving unit 21, wherein the first sound pickup unit 11 and the second sound pickup unit 12 of the collecting unit 10 are communicatively connected to the voice receiving unit 21, respectively, so that the voice receiving unit 21 receives the voice command collected by the first sound pickup unit 11 and the voice command collected by the second sound pickup unit 12 of the collecting unit 10.

Note that, when the driver of the vehicle 200 issues the voice command, the first sound pickup unit 11 and the second sound pickup unit 12 each receive the voice command independently, and the voice command collected by the first sound pickup unit 11 is named as a first voice command 301, the voice command collected by the second sound pickup unit 12 is named as a second voice command 302, and the voice receiving unit 21 is allowed to receive the first voice command 301 and the second voice command 302 from the first sound pickup unit 11 and the second sound pickup unit 12, respectively.

Preferably, the voice receiving unit 21 is connected to the first sound pickup unit 11 and the second sound pickup unit 12 by a wired connection, and it will be understood by those skilled in the art that the voice receiving unit 21 may be connected to the first sound pickup unit 11 and the second sound pickup unit 12 by a wireless connection, such as, but not limited to, a bluetooth connection, a WiFi connection, or the like.

Referring to fig. 4 and 5, the processing unit 20 further includes a comparing unit 22, the comparing unit 22 receives the first voice command 301 and the second voice command 302 from the voice receiving unit 21, and the comparing unit 22 is capable of processing the first voice command 301 received from the first sound pickup unit 11 and the second voice command 302 received from the second sound pickup unit 12 to generate the control command, and transmitting the control command to the output unit 30.

In a preferred example of the speech processing system 100 of the present invention, the comparing unit 22 can compare the speech quality of the first speech command 301 and the second speech command 302, and reserve one speech command with better sound quality and discard the speech command with worse sound quality. The criterion for judging the quality of the voice by the comparing unit 22 includes, but is not limited to, the size of the sound, the frequency of the sound, the size of the background sound, etc. The method for determining the quality of the voice may be to select several same time nodes from the first voice command 301 and the second voice command 302 for comparison, so as to generate the control command.

For example, if the comparison unit 22 compares that the voice quality of the first voice command 301 is better than the voice quality of the second voice command 302, the comparison unit transfers the first voice command 301 to the output unit 30, and discards the second voice command 301.

It should be noted that the comparing unit 22 is further capable of individually comparing the second voice command 302 or the first voice command 301 received by the second sound pickup unit 11 after passing through the second sound pickup unit 12 within a predetermined period of time, and transmitting the result of the comparison to the output module 30. In a preferred embodiment of the speech processing system 100 of the present invention, the comparing unit 22 is configured to compare the frequencies of the speech of the respective components of the second speech instruction 302 received within a predetermined period of time, and select a portion with better quality of the speech with the same frequency as the component of the speech instruction. As will be appreciated by those skilled in the art, criteria for determining whether a voice quality is good include, but are not limited to, clarity of sound, loudness of sound, and the like.

For example, the second voice command 302 is composed of a plurality of voices with different frequencies, for example, the second voice command 302 is composed of Y1, Y2, Y3, and Y1 voices with the same frequency as Y1 and smaller loudness, wherein the Y1 part is an echo corresponding to the Y1 part in the second voice command 302 collected by the second sound pickup unit 12, and the comparing unit 22 further selects the Y1 part with higher loudness as the second voice command 302 by comparing the second voice command 302 alone.

In the manner described above, it will be possible to avoid affecting the quality of the second voice command 302 due to the presence of echoes.

It should be noted that the speech processing system 100 provided by the present invention further has a function of recognizing a specific person's speech command, for example, if the vehicle 200 equipped with the speech processing system 100 of the present invention is owned by Wang Mou and the original speech stored in the steering wheel-based speech processing system 100 is a speech command issued by Wang Mou, then Li Mou does not recognize the steering wheel-based speech processing system 100 and does not control the vehicle 200 to perform a corresponding action when issuing the speech command.

That is, before using the steering wheel-based speech processing system 100 of the present invention, an original speech command needs to be input in advance, the acquisition unit 10 acquires the original speech command, and transmits the acquired original speech command to the speech receiving unit 21 for storage.

The processing unit 20 further includes a judging unit 23, where the judging unit 23 is configured to receive the voice command processed by the comparing unit 22 from the comparing unit 22, compare the voice command with an original voice command stored in the voice receiving unit 21 to determine whether the voice command belongs to the same sender, generate the control command if the voice command belongs to the same sender with the original voice command, and transmit the control command to the output unit 30, and if the voice command does not belong to the same sender, no action occurs.

The output unit 30 is communicatively connected to a voice control system 700 and outputs the control instructions to the voice processing system 700, wherein the voice processing system 700 is capable of controlling the vehicle 200 based on the voice instructions output by the output unit 30.

It will be appreciated by those skilled in the art that based on the voice command output by the output unit 30, the voice processing system 700 controls the vehicle to perform actions that are either driving-related, such as passing, parking, changing lanes, etc., or driving-independent, such as playing music, opening or closing windows, adjusting seats, etc.

In another preferred example of the voice processing system 100 of the present invention, the comparing unit 22 is capable of correcting the first voice command 301 received from the first sound pickup unit 11 and the second voice command 302 received from the second sound pickup unit 12 to improve the sound quality of the voice command collected by the collecting unit 10. For example, in a specific example of the speech processing system 100 of the present invention, the comparing unit 22 may perform the superimposition processing on the first speech instruction 301 and the second speech instruction 302 to correct the first speech instruction 301 and the second speech instruction 302. For example, in another specific example of the speech processing system 100 of the present invention, the comparison unit 22 may perform a difference set process on the first speech instruction 301 and the second speech instruction 302 to correct the first speech instruction 301 and the second speech instruction 302. Specifically, the comparing unit 22 may compare the first voice command 301 and the second voice command 302 to determine which sounds are command sounds and which sounds are background sounds, and then the comparing unit 22 may modify the voice command and generate the control command by removing the background sounds.

Referring to fig. 5, according to another aspect of the present invention, the present invention further provides a steering wheel-based voice processing method, wherein the voice processing method includes the steps of:

step 501: forming a sound pickup field in a riding space of a vehicle by arranging at least one first sound pickup unit in a middle control screen of the vehicle or in the vicinity of the middle control screen and at least one second sound pickup unit in at least one steering wheel of the vehicle;

step 502: collecting a first voice instruction and a second voice instruction collected by the first sound pickup unit and the second sound pickup unit respectively;

step 503: generating a control instruction by comparing and optimizing the first voice instruction and the second voice instruction; and

step 504: and outputting the control instruction.

And wherein in the step 302, when a driver approaches the steering wheel 202 of the vehicle 200, the second sound pickup unit 12 picks up a sound emitted by the driver, and the first sound pickup unit 11 picks up a background sound. When the driver gets far from the steering wheel 202 of the vehicle 200, the second sound pickup unit 12 picks up a background sound, and the first sound pickup unit 11 picks up a sound emitted from the driver.

Fig. 6 and 7 disclose a second preferred embodiment of the steering wheel based speech processing system 100 according to the present invention, wherein the speech processing system 100 comprises a collecting unit 10 and a processing unit 20, the collecting unit 10 and the processing unit 20 being communicatively connected to each other. The collecting unit 10 collects at least one voice command sent by a person on the vehicle 200, and transmits the voice command to the processing unit 20, and the processing unit 20 generates a control command by processing the voice command, and controls the vehicle 200 to generate a corresponding action based on the control command.

The pickup unit 10 includes at least one first pickup unit 11 provided to the center control panel 203 of the vehicle 200 or provided in the vicinity of the center control panel 203 and at least one second pickup unit 12 provided to the steering wheel 202 of the vehicle 200. The first sound pickup unit 11 and the second sound pickup unit 12 cooperate with each other to form the sound pickup field 500 in the seating space of the vehicle 200 for collecting the voice command issued by the occupant in the seating space of the vehicle 100.

The processing unit 20 includes a voice receiving unit 21 and a judging unit 23, the voice receiving unit 21 and the judging unit 23 being communicably connected to each other, and the voice receiving unit 21 being communicably connected to the first sound pickup unit 11 and the second sound pickup unit 12 of the collecting unit 10. The voice receiving unit 21 is configured to receive a first voice command 301 collected by the first sound pickup unit 11 and a second voice command 302 collected by the second sound pickup unit 12. The judging unit 23 is configured to judge whether the voice command and an original voice command belong to the same issuer, and generate the control command, and the judging unit 23 is communicably connected to the output unit 30, wherein the output unit 30 outputs the control command judged by the judging unit 23.

The difference between the speech processing system 100 of the present preferred embodiment and the speech processing system 100 of the first preferred embodiment is that the processing unit 20 further includes an integrating unit 27, the integrating unit 27 is capable of receiving the first speech command 301 and the second speech command 302 from the speech receiving unit 21, comparing the speech quality of the first speech command 301 and the speech quality of the second speech command 302, intercepting the better quality part of the first speech command 301 and the better quality part of the second speech command 302 to form a complete third speech command 303, and using the third speech command 303 as the control command, wherein the output unit 30 is communicatively connected to the integrating unit 27, so as to control the vehicle 200 by the output integrated control command.

For example, the position of the driver of the vehicle 200 in the riding space may be changed in the course of operating the steering wheel 202 of the vehicle 200 by the driver of the vehicle 200 and issuing the voice command desired to control the vehicle 200. For example, the front half of the time when the driver gives the voice command may face forward, and the rear half of the time when the driver gives the voice command may face backward, that is, the front half of the content when the driver gives the voice command forward and the rear half of the content when the driver gives the voice command backward, which may result in that the quality of the voice command collected by the first sound pickup unit 11 and the second sound pickup unit 12 in different time periods during the time when the driver gives the voice command is different. If the voice command collected by the first sound pickup unit 11 and the second sound pickup unit 12 is processed and judged at this time, it is likely that only half of the voice command can be received, the voice command cannot be correctly recognized or the voice command cannot be incorrectly recognized, and great inconvenience is caused to the driver.

In the preferred example of the speech processing system 100 of the present invention, the integrating unit 27 is capable of integrating the speech commands collected by the first sound pickup unit 11 and the second sound pickup unit 12 to generate the control command with a complete quality that can be recognized.

The determining unit 23 receives the third voice command 303 from the integrating unit 27, compares the third voice command 303 with the original voice command, and transmits the third voice command 303 to the processing unit 24 when determining that the third voice command 303 and the original voice command are issued by a unified issuer, wherein the processing unit 24 is configured to control the vehicle 200 to generate a corresponding action according to the third voice command 303, and does not transmit the control command to the output unit 30 when determining that the third voice command 303 and the original voice command are issued by different issuers, and the vehicle 200 does not generate an action.

Referring to fig. 7, according to another aspect of the present invention, the present invention further provides a steering wheel-based voice processing method, wherein the voice processing method includes the steps of:

Step 701: collecting a first voice command 301 and a second voice command 302 from a first sound pickup unit 11 and a second sound pickup unit 12, respectively, wherein the first sound pickup unit 11 is disposed at the center control panel 203 of the vehicle 200 or is disposed in the vicinity of the center control panel 203, and the second sound pickup unit 12 is disposed at the steering wheel 202 of the vehicle 200;

step 702: integrating the first voice command 301 and the second voice command 302 to generate a third voice command 303; and

step 703: and outputting the third voice instruction.

Referring to fig. 1 to 7, a third preferred embodiment of a steering wheel-based speech processing system 100 according to the present invention is illustrated, wherein the speech processing system 100 includes a collecting unit 10 and a processing unit 20, the collecting unit 10 and the processing unit 20 are communicatively connected to each other, the collecting unit 10 is configured to collect at least one speech command issued by a person on the vehicle 200 and transmit the speech command to the processing unit 20, and the processing unit 20 is communicatively connected to the output unit 30, and the speech command output by the output unit 30 is used to control the vehicle 200 to generate a corresponding action.

The pickup unit 10 includes at least a first pickup unit 11 provided to the center control panel 203 of the vehicle 200 or provided in the vicinity of the center control panel 203 and a second pickup unit 12 provided to the steering wheel 202 of the vehicle 200. The first pickup unit 11 and the second pickup unit 12 cooperate with each other to form a sound field 500 in the seating space of the vehicle 200 for collecting the driver's emission in the seating space of the vehicle 200 near the steering wheel 202.

The processing unit 20 includes a voice receiving unit 21 and a judging unit 23, the voice receiving unit 21 and the judging unit 23 being communicably connected to each other, and the voice receiving unit 21 being communicably connected to the first sound pickup unit 11 and the second sound pickup unit 12 of the collecting unit 10. The voice receiving unit 21 is configured to receive a first voice instruction 301 collected by the first sound pickup unit 11 and a second voice instruction 302 collected by the second sound pickup unit 12. The judging unit 23 judges whether the same as an original voice instruction belongs to the same issuer or not, and generates the control instruction.

Further, according to another aspect of the present invention, there is provided a steering wheel based voice control system, wherein the voice control system comprises the steering wheel based voice processing system described above and a control unit 40, wherein the control unit 40 is communicatively connected to the output unit 30, wherein the control unit 40 controls the vehicle 200 according to the control instruction output by the output unit 30.

It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are by way of example only and are not limiting. The objects of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been shown and described in the examples and embodiments of the invention may be modified or practiced without departing from the principles described.

Claims

1. A steering wheel based speech processing system comprising:

the collecting unit comprises two sound pickup units, wherein one sound pickup unit is arranged on a middle control screen of a vehicle or is adjacently arranged on the middle control screen and is used for collecting a first voice instruction, and the other sound pickup unit is arranged on a steering wheel of the vehicle and is used for collecting a second voice instruction;

Wherein the sound pickup unit provided to the center control panel of the vehicle or provided adjacently to the center control panel is a first sound pickup unit, and the sound pickup unit provided to the steering wheel is a second sound pickup unit;

one of the first sound pickup unit and the second sound pickup unit is a main sound pickup unit, and the other sound pickup unit is an auxiliary sound pickup unit; the first pickup unit and the second pickup unit are each switchable between a main pickup unit and an auxiliary pickup unit; the main pickup unit is used for collecting the voice instruction sent by the driver, and the auxiliary pickup unit is used for collecting the voice instruction sent by the driver and background sounds except the voice instruction sent by the driver; the main pickup unit faces toward or near the driver's face; the auxiliary pickup unit is not oriented to the face of the driver; the first pickup unit and the second pickup unit are capable of switching between the main pickup unit and the auxiliary pickup unit in accordance with a distance between the driver and the pickup unit;

the second pickup unit is adjustably arranged on the steering wheel, so that a sound receiving field formed by the first pickup unit and the second pickup unit is a dynamic sound receiving field;

2. The speech processing system of claim 1 wherein the processing unit compares the sound quality of the first speech command to the sound quality of the second speech command to generate a control command for controlling the vehicle based on the better one of the first speech command and the second speech command.

3. The speech processing system of claim 1 wherein the processing unit superimposes the first speech command and the second speech command to generate the control command for controlling the vehicle.

4. The speech processing system of claim 1 wherein the processing unit performs a difference processing on the first speech command and the second speech command to generate the control command for controlling the vehicle.

5. The speech processing system of claim 1 wherein the processing unit is capable of intercepting a better quality segment of the first speech command and a better quality segment of the second speech command to generate the control command for controlling the vehicle.

6. The speech processing system of claim 2 wherein the control unit compares the first speech instruction to the second speech instruction based on the condition that: the sound size, the frequency of the sound, the background sound size.

7. A voice control system, wherein the voice control system comprises:

the speech processing system of any one of claims 1 to 6; and

8. A steering wheel based speech processing method, the speech processing method comprising the steps of:

(d) Outputting the control instruction;

the second pickup unit is adjustably disposed on the steering wheel, so that the sound pickup field formed by the first pickup unit and the second pickup unit is a dynamic sound pickup field.

9. The method of claim 8, wherein in the step (a), at least one third pickup unit is disposed on at least one steering wheel to form the sound field by the third pickup unit and the second pickup unit.

10. The method of claim 9, wherein in the method, the second pickup unit is adjustably disposed on the steering wheel such that the sound pickup field formed by the second pickup unit and the third pickup unit is a dynamic sound pickup field.

11. The method of claim 9, wherein in the method, the third sound pickup unit is adjustably disposed on the steering wheel, such that the sound pickup field formed by the second sound pickup unit and the third sound pickup unit is a dynamic sound pickup field.

12. The speech processing method of claim 10 wherein in the method above the third pickup unit is adjustably positioned to the steering wheel such that the sound pickup field formed by the second pickup unit and the third pickup unit is the dynamic sound pickup field.

13. The speech processing method of any one of claims 8 to 12 wherein in step (c), further comprising the step of: and comparing the sound quality of a first voice command acquired by the first sound pickup unit with the sound quality of a second voice command acquired by the second sound pickup unit, and generating the control command according to the voice command with better sound quality in the first voice command and the second voice command so as to control the vehicle.

14. The speech processing method of any one of claims 8 to 12 wherein in step (c), further comprising the step of: and superposing a first voice command acquired by the first pickup unit and a second voice command acquired by the second pickup unit to generate the control command for controlling the vehicle.

15. The speech processing method of any one of claims 8 to 12 wherein in step (c), further comprising the step of: the difference set processes a first voice command acquired by the first pickup unit and a second voice command acquired by the second pickup unit to generate the control command for controlling the vehicle.

16. The speech processing method of any one of claims 8 to 12 wherein in step (c), further comprising the step of: and intercepting the fragment with better sound quality in the first voice command and the fragment with better sound quality in the second voice command to generate the control command so as to control the vehicle.

17. A method of steering wheel based voice control, wherein the method comprises:

a method of speech processing according to any one of claims 8 to 16, generating a control instruction; and

And controlling the vehicle by executing the control instruction.