CN108725340B

CN108725340B - Vehicle voice processing method and system

Info

Publication number: CN108725340B
Application number: CN201810295572.5A
Authority: CN
Inventors: 夏国庆
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: 2022-04-12
Anticipated expiration: 2038-03-30
Also published as: CN108725340A

Abstract

The invention provides a vehicle voice processing method and a system thereof, wherein the vehicle voice processing method comprises the following steps: (a) acquiring a time corresponding to each first audio signal according to the first audio signals from different radio equipment and from the same sound source; and (b) adjusting to a same time at least one of said times of each of said first audio signals being different from the others.

Description

Vehicle voice processing method and system

Technical Field

The invention relates to the field of vehicle voice, in particular to a vehicle voice processing method and a vehicle voice processing system.

Background

Most vehicles today are equipped with a sound receiving device, commonly used as a microphone. In addition, with the development of technology, there is a demand for portability of operation on the one hand, and with the development of unmanned technology, a vehicle voice control system has come to be available, and a user can directly control a vehicle by issuing a voice command, so that the user can control the vehicle without directly operating the vehicle. From the side, speech processing requirements for vehicle speech systems are also increasing, the operational accuracy and safety of which are closely related to the processing power for the received speech signals.

First, there are various sounds in the vehicle, sounds made by the operation of equipment in the vehicle, noises outside the vehicle, sounds played by entertainment equipment in the vehicle, sounds of passenger conversations in the vehicle, and even sounds made by a telephone call when a passenger is on a telephone call, which all cause interference. On the one hand, the sound receiver located at a fixed position cannot collect sound with a small volume at a position relatively far away from the sound receiver because of its position, for example, a passenger in the rear row wants to send a voice command, but when the sound receiver is located at the front position of the main driver, the sound receiver may not accurately recognize the voice command of the passenger in the case that the sound sent by the passenger in the rear row is relatively small.

Secondly, when a user in the vehicle, for example, a passenger or a driver, makes a sound, the vehicle is a relatively closed space, the sound wave is reflected back and forth in the vehicle, for the same audio signal generated by the same sound source, the radio equipment may receive signals with different intensities for multiple times, and interference is also caused to the radio effect of the radio equipment to a certain extent, especially under the condition that more than one sound source is generated from the vehicle, the audio signal received by the radio equipment is more complicated, and finally the accuracy of recognition of the voice command is affected. After the sound receiving device receives the relevant audio signals, a vehicle voice processing system needs to process the audio signals. The processed audio signal, if it includes a voice command, is sent to the associated device to execute the voice command.

The problem follows that the devices in the vehicle have their own working time axes in cooperation, i.e. the radio device has a working time axis, a processor for processing the audio signal has a working time axis, the device for receiving the relevant voice commands has a working time axis, these working time axes are not kept identical and a large deviation of the time axes, which are comparable to each other at first, may occur as time errors accumulate. For example, when the driver signals a vehicle turn by a voice command, however, since the operation time axis of the device processing the voice command is one minute later than the time axis of the driver, that is, the processing device may start executing the voice command after receiving the voice command for one minute. Obviously, such a speech processing method may pose a significant threat to the life safety of the driver.

Disclosure of Invention

An objective of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can provide a plurality of radio devices to improve the accuracy of voice collection.

Another object of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can correct the working time axis of each device to ensure the effectiveness and stability of the whole system operation.

Another object of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system is capable of processing a received audio signal by performing a timing process on the received audio signal of the same sound source.

Another object of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can acquire respective operation time axes of the sound pickup devices receiving audio signals of the same sound source to correct them.

Another objective of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can confirm a main radio device of the radio devices according to an audio signal received, and adjust other radio devices according to an operation time axis of the main radio device.

Another objective of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can process an audio signal collected by the main radio device in cooperation with each audio signal collected by other radio devices.

Another object of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice system can correct the working time axes between a plurality of the radio devices and at least one broadcasting device to cooperate with each other.

Another objective of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can respectively confirm working time axes of a broadcasting device and a radio device according to a received audio signal and a played audio signal.

Another object of the present invention is to provide a vehicle voice processing method and system thereof, wherein the vehicle voice processing system can process the received audio signals before and after the same sound source to eliminate the influence of echo.

According to an aspect of the present invention, there is provided a vehicle voice processing method, including the steps of:

(a) acquiring a time corresponding to each first audio signal according to the first audio signals from different radio equipment and from the same sound source; and

(b) at least one of the times of each of the first audio signals is different from the others, and is adjusted to a same time for subsequent processing.

According to an embodiment of the invention, the time is a time of receiving the first audio signal.

According to an embodiment of the invention, the time is a time at which a characteristic frequency of the first audio signal is received.

According to an embodiment of the present invention, the step (a) includes the steps of:

(a.1) noise reducing processing based on the first audio signal to generate a second audio signal when the first audio signal received for the same radio includes overlapping portions; and

(a.2) obtaining a corresponding time based on the second audio signal.

According to an embodiment of the invention, the step (a.1) is implemented as: the first audio signal received for the same radio includes overlapping portions that are separated based on the first audio signal to generate a second audio signal.

According to an embodiment of the invention, the step (a.1) is implemented as:

the first audio signal received by the same radio equipment comprises an overlapping part, and the first audio signal is processed in an overlapping mode to generate a second audio signal.

According to an embodiment of the present invention, the method further comprises a step (c), wherein the step (c) comprises:

confirming a main radio device and at least one auxiliary radio device according to the first audio signal received by each radio device; and

based on a main voice instruction of the first audio signal of the main radio equipment and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio equipment which are adjusted to the same time, determining an execution voice instruction according to the better voice instruction in the main voice instruction and the auxiliary voice instruction, so as to control the vehicle.

According to an embodiment of the present invention, the method further comprises a step (d), wherein the step (d) comprises:

(d.1) collecting a first broadcast audio signal from a broadcast device based on a broadcast voice command of the first audio signal;

(d.2) acquiring a work time axis information of the broadcasting equipment based on the first broadcasting audio signal and acquiring a work time axis information corresponding to the radio equipment based on the first audio signal, and comparing whether the work time axis of the broadcasting equipment is consistent with the work time axis of each radio equipment; and

(d.3) if there is an inconsistency, adjusting to a same working time axis.

According to an embodiment of the invention, the step (d.2) is implemented as:

when the first broadcast audio signal received by the same radio equipment comprises an overlapping part, generating a second broadcast audio signal for the first broadcast audio signal in a noise reduction processing mode;

when the first audio signal received by the same radio equipment comprises an overlapping part, generating a second audio signal by the first audio signal in a noise reduction processing mode; and

and acquiring working time axis information of the radio equipment based on a second broadcast audio signal of the radio equipment and the second audio signal of the radio equipment.

According to an embodiment of the present invention, further comprising a step (e), wherein the step (e) comprises the steps of:

acquiring working time axis information corresponding to each radio equipment according to a first audio signal from the same sound source received by at least two radio equipments; and

and if at least one of the working time axes of the radio equipment is different from the others, adjusting to the same working time axis.

According to another aspect of the present invention, there is provided a vehicle speech processing system, wherein the vehicle speech processing system comprises:

at least two radio devices; and

a processing unit, wherein the processing unit and the sound receiving devices are communicably connected to each other, the processing unit acquires times corresponding to the respective first audio signals based on a first audio signal from the same sound source received by the respective sound receiving devices, and adjusts to a same time if at least one of the times of the respective first audio signals is different from the others.

According to an embodiment of the present invention, the processing unit includes an obtaining module, a determining module and an adjusting module, wherein the obtaining module obtains a time corresponding to each of the first audio signals based on each of the first audio signals, the determining module determines whether at least one of the times of each of the first audio signals is different from others to obtain a determination result, and the adjusting module processes the time of each of the first audio signals according to the determination result to make the times of each of the first audio signals consistent.

According to an embodiment of the present invention, the audio signal processing device further includes a processing module, and the processing module processes each adjusted first audio signal to obtain an execution voice instruction.

According to an embodiment of the present invention, the processing module includes a confirming module and a generating module, wherein the confirming module confirms a main radio device and at least one auxiliary radio device according to the first audio signal received by each of the radio devices, and the generating module confirms an execution voice command according to a main voice command of the first audio signal collected by the main radio device and an auxiliary voice command of the first audio signal collected by the auxiliary radio device, and determines a better quality one of the main voice command and the auxiliary voice command as an execution voice command for controlling the vehicle.

According to an embodiment of the present invention, the audio signal processing apparatus further includes a noise reduction module, wherein the noise reduction module is communicably connected to the sound reception apparatus and the acquisition module, respectively, and if the first audio signal includes an overlapping portion, the noise reduction module performs noise reduction processing on the first audio signal to generate a second audio signal, the acquisition module acquires a time corresponding to each of the second audio signals based on each of the second audio signals, the determination module determines whether at least one of the times of each of the second audio signals is different from others to obtain a determination result, and the adjustment module performs processing on the time of each of the second audio signals according to the determination result to make the times of each of the second audio signals consistent.

According to an embodiment of the present invention, the processing unit includes an obtaining module, a determining module and an adjusting module, wherein the obtaining module obtains a working time axis information corresponding to each of the radio devices based on each of the first audio signals, the determining module determines whether at least one of the working time axes of each of the radio devices is different from others to obtain a determination result, and the adjusting module processes the working time axes of each of the radio devices according to the determination result to make the working time axes of each of the radio devices consistent.

According to an embodiment of the present invention, the processing unit further comprises a processing module and an announcement equipment adjusting module, wherein the processing unit is communicatively connected to the adjusting module, when the processing unit derives a play voice command based on the adjusted first audio signal of each of the sound receiving devices, the radio equipment receives a first broadcast audio signal from broadcast equipment, the acquisition module acquires working time axis information of the broadcast equipment based on the first broadcast audio signal and acquires working time axis information corresponding to the radio equipment from the first audio signal, the judging module judges whether the working time axis of the broadcasting equipment is consistent with the working time axis of each radio equipment or not and obtains a judging result, and the broadcasting equipment adjusting module adjusts the radio equipment and the broadcasting equipment to a same working time axis according to the judgment result.

According to an embodiment of the present invention, the apparatus further comprises a processing module and an adjusting module of broadcasting equipment, wherein the processing unit is communicatively connected to the adjusting module, when the processing unit derives a play voice instruction based on each of the adjusted first audio signals, the radio equipment receives a first broadcast audio signal from broadcast equipment, the acquisition module acquires working time axis information of the broadcast equipment based on the first broadcast audio signal and acquires working time axis information corresponding to the radio equipment from the first audio signal, the judging module judges whether the working time axis of the broadcasting equipment is consistent with the working time axis of each radio equipment or not and obtains a judging result, and the broadcasting equipment adjusting module adjusts the radio equipment and the broadcasting equipment to a same working time axis according to the judgment result.

According to an embodiment of the present invention, further comprising a noise reduction module, wherein the noise reduction module is communicatively connected to the broadcasting device and the acquisition module respectively, if the first broadcast audio signal comprises an overlapping portion, the noise reduction module performs noise reduction processing on the first broadcast audio signal and the first audio signal respectively to generate a second broadcast audio signal and a second audio signal, the acquisition module acquires working time axis information of the broadcasting equipment based on the second broadcasting audio signal and acquires working time axis information corresponding to the radio equipment from the second audio signal, the judging module judges whether the working time axis of the broadcasting equipment is consistent with the working time axis of each radio equipment or not and obtains a judging result, and the broadcasting equipment adjusting module adjusts the radio equipment and the broadcasting equipment to a same working time axis according to the judgment result.

According to an embodiment of the present invention, the sound receiving device further comprises an identification module, wherein the identification module is communicably connected to the sound receiving device, the identification module identifies whether a first audio signal received by the sound receiving device is from the same sound source and obtains an identification result, and sends the identification result to the acquisition module, and the acquisition module acquires the time of the corresponding first audio signal from the same sound source.

Drawings

FIG. 1 is a schematic diagram of a vehicle speech processing system according to a preferred embodiment of the present invention.

FIG. 2 is a block diagram of a vehicle speech processing system according to a preferred embodiment of the present invention.

FIG. 3A is a diagram illustrating a method for processing speech of a vehicle according to a preferred embodiment of the present invention.

FIG. 3B is a diagram illustrating a vehicle speech processing method according to a preferred embodiment of the present invention.

FIG. 4 is a diagram illustrating an application of a speech processing system for a vehicle according to a preferred embodiment of the present invention.

FIG. 5 is a schematic diagram of an application of a vehicle speech processing system according to a preferred embodiment of the present invention.

Detailed Description

The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as 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 understood by those skilled in the art that in the present disclosure, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for ease of description and simplicity of description, and do not indicate or imply that the referenced devices or components must be in a particular orientation, constructed and operated in a particular orientation, and thus the above terms are not to be construed as limiting the present invention.

It is understood that the terms "a" and "an" should be interpreted as meaning that a number of one element or element is one in one embodiment, while a number of other elements is one in another embodiment, and the terms "a" and "an" should not be interpreted as limiting the number.

Referring to fig. 1 of the drawings of the present specification, a vehicle speech processing system 100 according to a preferred embodiment of the present invention is disclosed and illustrated in the following description, wherein the vehicle speech processing system 100 is adapted to a vehicle 200 for receiving at least one audio signal from a driver of the vehicle 200 or a passenger of the vehicle 200 or a broadcast device in the vehicle 200, and adjusting an operation time axis corresponding to each device according to the audio signal, so as to make it more efficient to execute a speech command of the audio signal in a subsequent execution process.

Further, the vehicle 200 includes a vehicle body 201, at least one seat 202 and a middle control panel 203, wherein the seat 202 and the middle control panel 203 are respectively disposed on the vehicle body 201, and the seat 202 and the middle control panel 203 are both disposed on the vehicle body 201, the seat 202 allows a user to sit thereon, for example, the user can sit on the vehicle by sitting on the seat 202, and the middle control panel 203 allows the user to view and control the state of the vehicle 200. Compared with the conventional vehicle voice processing system 100, the vehicle voice processing system 100 of the invention arranges at least two radio devices 10 on the vehicle 200 to receive the voice command at a position as close to the voice command sender as possible, thereby improving the efficiency, accuracy and success rate of recognizing the voice command.

With further reference to fig. 1, the number of the seats 202 of the vehicle may be five, wherein the seats 202 are defined in the vehicle speech processing system 100 of the present invention as a cockpit seat 2021, a set of cockpit seats 2022, a rear row first seat 2023, a rear row second seat 2024 and a rear row third seat 2025, wherein the cockpit seat 2021 and the cockpit seat 2022 are located at the front portion of the vehicle body 201, the rear row first seat 2023, the rear row second seat 2024 and the rear row third seat 2025 are located adjacent to each other at the rear row of the vehicle body 201. One radio equipment 10 is arranged at the front part of the vehicle body 201, and the other radio equipment 10 is arranged at the rear part of the vehicle body 201, so that the recognition efficiency of the vehicle voice processing system 100 is improved by arranging the two radio equipments 10 at different positions. Alternatively, one of the radio sets 10 may be disposed on the center control panel 203, and the other radio set 10 may be disposed on the seat 202. It will be understood by those skilled in the art that the location of the sound receiving unit 10 is not a limitation of the present invention.

It is worth mentioning that the radio receiver 10 is rotatably connected to the vehicle body 201, either the seat 202 or the center control panel 203. By detecting the sitting posture of the user with a detecting device, the orientation of the sound receiving device 10 can be changed to obtain a better sound receiving effect.

Referring to fig. 3A, according to an aspect of the present invention, there is provided a vehicle voice processing method, wherein the vehicle voice processing method includes the steps of:

(a) acquiring a time corresponding to each first audio signal according to the first audio signals from different radio equipment 10 and from the same sound source; and

The vehicle voice processing system 100 obtains the time corresponding to each audio signal directly according to the time of receiving an audio signal from the same sound source by the sound receiving device 10, for example, the time of receiving an audio signal from a sound source by one sound receiving device 10 is 10 o 'clock, and the time of receiving an audio signal from the same sound source by another sound receiving device 10 is 10 o' clock 05 minutes, and by using a detection device, it can be known that the theoretical time from the same sound source to reach two sound receiving devices 10 should be the same, that is, two sound receiving devices 10 should receive the audio signals in the same time. The vehicle speech processing system 100 is capable of correcting this. If the vehicle speech processing system 100 does not correct it, the subsequent processing device may process it at 10 o' clock 05 minutes during the subsequent processing, which may be a lag in the user experience for the user.

With further reference to fig. 1 and 2, a preferred embodiment of the speech processing system provided by the present invention is further illustrated in the following description, wherein the vehicle speech processing system 100 comprises a collecting unit and a processing unit 20, wherein the collecting unit and the processing unit 20 are communicatively connected to each other, wherein the collecting unit is used for collecting or receiving or identifying an audio signal, the processing unit 20 is used for obtaining a time data of the audio signal based on the audio signal, and if the time data of the audio signals from the same sound source are not consistent, the processing unit 20 adjusts the audio signals to be consistent for subsequent processing steps.

Specifically, the collecting unit includes at least two radio devices 10, wherein the radio devices 10 are respectively disposed at different positions of the vehicle, and may be one radio device 10 disposed on the central control panel 203 and one radio device 10 disposed on the seat 202, and when the vehicle driver, or the vehicle passenger, or other broadcasting devices in the vehicle, sends out an audio signal, the radio devices 10 cooperate to complete the collection of the audio signal. Subsequently, the audio signals collected by the radio devices 10 can be mutually modified by the processing unit 20 to provide efficiency and accuracy of the audio signals processed by the vehicle voice processing system 100, so as to provide user experience for vehicle users and ensure safety during driving.

Further, the processing unit 20 includes an obtaining module 21, a judging module 22 and an adjusting module 23, wherein the obtaining module 21 is communicably connected to the sound receiving apparatus 10, wherein the obtaining module 21 obtains the time corresponding to each of the first audio signals based on each of the first audio signals, the judging module 22 judges whether at least one of the times of each of the first audio signals is different from others to obtain a judgment result, and the adjusting module 23 processes the time of each of the first audio signals according to the judgment result to make the time of each of the first audio signals consistent.

In some examples of the invention, the time is a time of receiving the first audio signal.

For example, the audio signal from the user is received by one of the audio receiving devices 10 at 10 o 'clock, the audio signal from the user is received by another of the audio receiving devices 10 at 10 o' clock 01, the identification module identifies the audio signals received by the radio equipment 10, and the identification result is that the audio signals come from the same user, the acquisition module 21 acquires the time of receiving the audio signal by each radio equipment 10, which is 10 o 'clock and 10 o' clock 01 minutes respectively, with a difference of 1 minute, the determination module 22 can determine the position between the user and each of the radio devices 10 by a detection device, if the distance between the user and the two sound receiving devices 10 is equal, the judging module 22 determines that the working time axes of the sound receiving device 10 and the sound receiving device 10 are different by one minute. The adjusting module 23 is communicably connected to the judging module 22 and the obtaining module 21, and the adjusting module 23 adjusts the time of each of the audio signals to the same time according to the judgment result.

It is understood that while the adjusting module 23 may adjust the time of each of the audio signals to a coordinated world, the adjusting module 23 may also adjust the time of each of the audio signals to be the same as one of the times of each of the audio signals. Say one of the audio signals has the highest volume, the time of the other audio signals can be adjusted to the time of this one of the audio signals.

In some examples of the present invention, the processing unit 20 further includes an identification module 24, wherein the identification module 24 is communicatively connected to the sound receiving devices 10, and identifies whether the audio signals are from the same sound source based on an audio signal received by each of the sound receiving devices 10, and the obtaining module 21 obtains a time information corresponding to each of the audio signals based on an audio signal of the same sound source received by each of the sound receiving devices 10.

For example, an audio signal from a user is received by one of the radio equipments 10, an audio signal from a user is received by another radio equipment 10, the audio signal received by each of the radio equipments 10 is identified by the identification module 24, as a result, the audio signal is from the same user, and the audio signal is identified by the identification module 24 based on information of a resonant peak, a fundamental frequency, a sound intensity, a sound length, and the like of the audio signal.

In some examples of the invention, the time is a time at which a characteristic frequency of the first audio signal is received.

For example, the characteristic formant of the audio signal received by one of the radio equipments 10 appears at 10 o ' clock, and the characteristic formant of the audio signal received by the other radio equipment 10 appears at 10 o ' clock 01 o ' clock, the determining module 22 can determine the position between the user and each of the radio equipments 10 by a detecting device, if the distance between the user and the two radio equipments 10 is equal, the determining module 22 determines that the working time axes of the two radio equipments 10 are different by one minute. The adjusting module 23 is communicably connected to the two sound receiving devices 10, and the working time axis of each of the sound receiving devices 10 can be respectively corrected to a same working time axis through the adjusting module 23. The adjusting module 23 can also correct the time value of an audio signal received by each of the sound receiving devices 10 only during the process of processing the audio signal, so as to facilitate the subsequent processing.

Further, referring to fig. 2 and 4, according to another embodiment of the present invention, the processing unit 20 includes a noise reduction module 25, wherein the noise reduction module 25 is communicatively connected to the sound receiving device 10, the noise reduction module 25 is communicatively connected to the obtaining module 21, and the noise reduction module 25 is used for performing a noise reduction preprocessing on the audio signal to facilitate subsequent processing thereof.

In a vehicle, there are many audio signals, especially in a vehicle with multiple passengers, different audio signals from different sound sources can be distinguished by a characteristic formant of each sound source, for the same sound source, an audio signal can be generated by resonance within a certain time, for the sound receiving device 10, based on the vehicle being a closed space, there is echo (may not be received by human ears, but for the sound receiving device 10 with higher precision, audio signals with different intensities from the same sound source), and an audio signal received by the sound receiving device 10 within a certain time period may itself include multiple superpositions of a signal. The noise reduction module 25 can perform a noise reduction process on the audio signal to obtain a noise-reduced audio signal, and the obtaining module 21 obtains time information corresponding to the audio signal based on the noise-reduced audio signal.

The noise reduction module 25 may separate overlapping portions of the audio signal to generate a noise reduced audio signal. The noise reduction module 25 may separate and align the superposition for the overlapping portions of the audio signal to generate a noise reduced audio signal. For example, the sound receiving device 10 receives an audio signal (a, b + a, c + b + a, c + b, c), and through a predetermined processing means, the original audio signal is found to be (a, b, c) that is superimposed twice in different time periods to generate the audio signal received by the sound receiving device 10. The noise reduction module 25 is capable of generating a noise reduced audio signal (a, b, c) based on the separation of the overlapping portions of the audio signal. The noise reduction module 25 may also separate and align the overlapping portions of the audio signals to generate a noise reduced audio signal (3a, 3b, 3c) so that a stronger audio signal can be obtained. It will be understood by those skilled in the art that a, b, and c are only abstract representations of characteristic information of an audio signal, and some loss of characteristic information may exist in echo in practical process.

Further, the vehicle voice processing system 100 includes a processing module 26, wherein the processing module 26 processes each of the audio signals after the adjusted time to obtain a processing result, which may be comparing the sound quality of the audio signals collected by each of the sound receiving devices 10, and selecting a better one of the sound quality to generate a voice command to control the vehicle. The processing module 26 may also superimpose the audio signals after the time adjustment to generate a voice command, so as to control the vehicle. The processing module 26 may also process the difference set of the audio signals after the adjustment time to generate a voice command to control the vehicle.

The processing module 26 is communicatively connected to the adjusting module 23 to process the audio signals from the same sound source of different sound receiving devices 10 adjusted to the same time axis. Alternatively, the audio signal may be the audio signal after noise reduction by the noise reduction module 25. The execution module performs a relevant operation on a corresponding device in the vehicle according to the voice instruction generated by the processing module 26.

Further, in some examples of the present invention, the processing module 26 includes a confirming module 261 and a generating module 262, wherein the confirming module 261 confirms a main radio receiver 10 and at least one auxiliary radio receiver 10 according to the first audio signal received by each of the radio receivers 10, and the generating module 262 confirms an execution voice command according to a main voice command of the first audio signal collected by the main radio receiver 10 and an auxiliary voice command of the first audio signal collected by the auxiliary radio receiver 10, and determines an execution voice command according to a better-quality one of the main voice command and the auxiliary voice command, so as to control the vehicle.

Further, with reference to fig. 5 and with continuing reference to fig. 2, the vehicle speech processing system 100 includes a public address adjustment module 27, wherein the public address adjustment module 27 is communicatively coupled to the determination module 22. The public address equipment adjusting module 27 is configured to adjust the public address equipment and the radio equipment 10 to the same working time axis.

For example, according to an embodiment of the present invention, each of the radio receiving devices 10 receives an audio signal from the same sound source, the obtaining module 21 obtains time information corresponding to each of the audio signals based on the audio signal, the determining module 22 obtains a determination result according to the time of each of the audio signals, when the time of the audio signal is different from other times, the adjusting module 23 adjusts the time of each of the audio signals to the same time, the processing module 26 obtains a voice instruction based on the audio signal at the same time, the voice instruction is "play a song", and the executing module controls a broadcasting device of the vehicle to execute the voice instruction. The broadcasting equipment can be a loudspeaker or a sound, when the broadcasting equipment outwards sends an audio signal as a sound source, each radio equipment 10 receives a broadcasting audio signal from the broadcasting equipment, the judgment module 22 defines the audio signal as a first audio signal based on the audio signal received by the radio equipment 10 for the first time from the user, the radio equipment 10 next receives the audio signal from the broadcasting equipment, the audio signal is defined as a first broadcasting audio signal, and the acquisition module 21 respectively acquires a working time axis of the radio equipment 10 and a working time axis of the broadcasting equipment based on the first audio signal and the first broadcasting audio signal. When the determining module 22 determines that a working time axis of the broadcasting device is different from a working time axis of the radio device 10, the broadcasting device adjusting module 27 adjusts the working time axis of the radio device 10 and the working time axis of the broadcasting device 30 to a same working time axis.

It is understood that the public address adjusting module 27 may adjust an operation time axis of a plurality of public address devices 30 based on the above adjusting manner, because the operation time axis of each public address device 30 may be different.

It is understood that the public address equipment adjusting module 27 may adjust the working time of the public address equipment 30 to be consistent with the working time axis of the radio equipment 10, and the adjustment may be performed by adjusting the working time axis of the public address equipment 30 and the working time axis of the radio equipment 10 to be the same, for example, based on a working time axis of a coordinated universal time, or by adjusting one of the public address equipment 30 and the radio equipment 10 to be the same as the working time axis of the other.

Referring to fig. 3B, according to an aspect of the present invention, there is provided a vehicle voice processing method, wherein the vehicle voice processing method includes the steps of:

(a) acquiring working time axis information corresponding to each radio equipment 10 according to the same first audio signal received by at least two radio equipment 10; and

(b) if at least one of the working time axes of the sound receiving devices 10 is different from the others, the working time axes are adjusted to be the same.

The vehicle voice processing system 100 controls the radio equipment 10 to achieve the purpose of mutual coordination. For example, each of the radio equipments 10 has its own working time axis, and the working time axes of each of the radio equipments 10 are not necessarily consistent, and for an audio signal sent by the same sound source, one radio equipment 10 receives the audio signal at a point 9 on its working time axis, and another radio equipment 10 receives the audio signal at a point 01 on its working time axis, because the working time axes of the two radio equipments 10 are not consistent, in a subsequent processing process, the radio equipment 10 possibly delayed by the working time axis may affect the entire processing efficiency, and the time for executing a corresponding instruction according to the audio signal may be correspondingly delayed. It may happen that the vehicle driver issues a voice command and the vehicle only gives feedback after five minutes. The vehicle speech processing system 100 can reduce this phenomenon by adjusting the operational timeline of the sound pickup device 10.

With further reference to fig. 1 and 2, a preferred embodiment of the speech processing system provided by the present invention is further illustrated in the following description, wherein the vehicle speech processing system 100 includes a collecting unit and a processing unit 20, wherein the collecting unit and the processing unit 20 are communicatively connected to each other, wherein the collecting unit is used for collecting or receiving or identifying an audio signal, the processing unit 20 obtains an operation time axis corresponding to one of the sound receiving devices 10 based on the audio signal, and if the operation time axes of the respective sound receiving devices 10 are not consistent, the processing unit 20 corrects the operation time axis.

Further, the processing unit 20 includes an obtaining module 21, a judging module 22 and an adjusting module 23, wherein the obtaining module 21 is communicably connected to the sound receiving device 10 for obtaining an operation time axis from the sound receiving device 10, the judging module 22 is communicably connected to the obtaining module 21, the judging module 22 judges whether at least one of the operation time axes of the sound receiving devices 10 is different from the others and obtains a judgment result, and the adjusting module 23 adjusts the operation time axis of the sound receiving device 10 to a same time axis according to the judgment result.

In some examples of the present invention, the processing unit 20 further includes an identification module 24, wherein the identification module 24 is communicatively connected to the sound receiving devices 10, and identifies whether the audio signals are from the same sound source based on an audio signal received by each of the sound receiving devices 10, and the obtaining module 21 obtains an operation time axis corresponding to each of the sound receiving devices 10 based on an audio signal of the same sound source received by each of the sound receiving devices 10.

In an embodiment of the invention, the obtaining module 21 is configured to obtain an operation time axis corresponding to each of the sound receiving devices 10 based on a time of the same first audio signal received by the sound receiving devices 10.

For example, the audio signal from the user is received by one of the audio receiving devices 10 at 10 o 'clock, the audio signal from the user is received by another of the audio receiving devices 10 at 10 o' clock 01, the identification module 24 identifies the audio signals received by the respective radio equipment 10, and as a result, the audio signals are from the same user, the acquisition module 21 acquires the time of receiving the audio signal by each radio equipment 10, which is 10 o 'clock and 10 o' clock 01 minutes respectively, with a difference of 1 minute, the determination module 22 can determine the position between the user and each of the radio devices 10 by a detection device, if the distances between the user and the two sound receiving devices 10 are equal, the judging module 22 determines that the working time axes of the two sound receiving devices 10 are different by one minute. The adjusting module 23 is communicatively connected to each of the sound receiving devices 10, and the working time axis of each of the sound receiving devices 10 can be respectively corrected to a same working time axis through the adjusting module 23. The adjusting module 23 can also correct the time value of an audio signal received by each of the sound receiving devices 10 only during the process of processing the audio signal, so as to facilitate the subsequent processing.

In some examples of the present invention, the obtaining module 21 obtains an operation time axis corresponding to each of the sound pickup devices 10 based on the time of the same first audio signal received by the sound pickup devices 10.

The obtaining module 21 obtains the time when a characteristic formant of the audio signal received by each radio equipment 10 appears, and obtains a working time axis corresponding to the radio equipment 10. For example, the characteristic formant of the audio signal received by the sound receiving device 10 appears at 10 o 'clock 01 o' clock, the determining module 22 can determine the position between the user and each of the sound receiving devices 10 by a detecting device, and if the distance between the user and the two sound receiving devices 10 is equal, the determining module 22 determines that the working time axes of the two sound receiving devices 10 are different by one minute. The adjusting module 23 is communicatively connected to each of the sound receiving devices 10, and the working time axis of each of the sound receiving devices 10 can be respectively corrected to a same working time axis through the adjusting module 23. The adjusting module 23 can also correct the time value of receiving an audio signal of each of the sound receiving devices 10 only during the process of processing the audio signal, so as to facilitate the subsequent processing.

In a vehicle, there are many audio signals, especially in a vehicle with multiple passengers, different audio signals from different sound sources can be distinguished by a characteristic formant of each sound source, for the same sound source, an audio signal can be generated by resonance within a certain time, for the sound receiving device 10, based on the vehicle being a closed space, there is echo (may not be received by human ears, but for the sound receiving device 10 with higher precision, audio signals with different intensities from the same sound source), and an audio signal received by the sound receiving device 10 within a certain time period may itself include multiple superpositions of a signal. The noise reduction module 25 can perform a noise reduction process on the audio signal to obtain a noise-reduced audio signal, and the obtaining module 21 obtains a working time axis corresponding to the radio device 10 based on the noise-reduced audio signal.

The noise reduction module 25 may separate overlapping portions of the audio signal to generate a noise reduced audio signal. The noise reduction module 25 may separate and align the superposition for the overlapping portions of the audio signal to generate a noise reduced audio signal. For example, the sound receiving device 10 receives an audio signal (a, b + a, c + b + a, c + b, c), and through a predetermined processing means, the original audio signal is found to be (a, b, c) that is superimposed twice in different time periods to generate the audio signal received by the sound receiving device 10. The noise reduction module 25 is capable of generating a noise reduced audio signal (a, b, c) based on the separation of the overlapping portions of the audio signals, and the noise reduction module 25 may also be capable of generating a noise reduced audio signal (3a, 3b, 3c) based on the separation of the overlapping portions of the audio signals and the aligned superposition, so that a stronger audio signal can be obtained. It will be understood by those skilled in the art that a, b, and c are only abstract representations of characteristic information of an audio signal, and some loss of characteristic information may exist in echo in practical process.

Further, the vehicle voice processing system 100 includes a processing module 26, wherein the processing module 26 processes each of the audio signals located on the same working time axis after adjustment to obtain a processing result, which may be comparing the sound quality of the audio signals collected by each of the radio devices 10, and selecting a better one of the audio signals to generate a voice command to control the vehicle. The processing module 26 can also superpose the audio signals collected by the radio equipment 10 on the same time axis to generate a voice command to control the vehicle. The processing module 26 can also process each audio signal collected by each radio device 10 in the same time axis difference set to generate a voice command to control the vehicle.

The confirmation module 261 can confirm a main radio equipment 10 and at least one auxiliary radio equipment 10 according to the volume of the first audio signal received by each radio equipment 10. The confirmation module 261 confirms the basis of the main radio device 10 and the auxiliary radio device 10 as follows: the volume of the first audio signal, the audio level and the background sound.

The generating module 262 can superimpose a main voice command and an auxiliary voice command of the first audio signal acquired by the main radio equipment 10 according to the main voice command of the first audio signal acquired by the auxiliary radio equipment 10 to generate an executing voice command for controlling the vehicle. The generating module 262 may also be configured to difference-process a main voice command and an auxiliary voice command of the first audio signal collected by the main radio equipment 10 to generate an execution voice command for controlling the vehicle according to the main voice command of the first audio signal collected by the auxiliary radio equipment 10 and the auxiliary voice command of the first audio signal collected by the auxiliary radio equipment 10. The generating module 262 may also intercept the segment with better sound quality of the main voice instruction and the segment with better sound quality of the auxiliary voice instruction to generate an executing voice instruction for controlling the vehicle according to a main voice instruction of the first audio signal acquired by the main radio equipment 10 and an auxiliary voice instruction of the first audio signal acquired by the auxiliary radio equipment 10.

It should be noted that the vehicle voice processing system 100 not only can time each radio receiver 10 so that each radio receiver 10 cooperates and cooperates with each other, but also the vehicle voice processing system 100 can cooperate and cooperate with the radio receiver 10 and at least one broadcasting device 30.

Further, with reference to fig. 5 and with continuing reference to fig. 2, the vehicle speech processing system 100 includes a public address adjustment module 27, wherein the public address adjustment module 27 is communicatively coupled to the determination module 22. The public address equipment adjusting module 27 is configured to adjust the public address equipment 30 and the radio equipment 10 to the same working time axis.

For example, according to an embodiment of the present invention, each of the radio receiving devices 10 receives an audio signal from the same sound source, the obtaining module 21 obtains a working time axis corresponding to each of the radio receiving devices 10 based on the audio signal, the determining module 22 obtains a determination result according to each working time axis, when the working time axis of at least one of the radio receiving devices 10 is different from others, the adjusting module 23 adjusts the working time axis corresponding to each of the radio receiving devices 10 to a same working time axis, the processing module 26 obtains a voice instruction based on the audio signal in the same working time axis, the voice instruction is "play a song", and the executing module controls a broadcasting device 30 of the vehicle to execute the voice instruction. The broadcasting device 30 may be a speaker or a sound, when the broadcasting device 30 emits an audio signal outwards as a sound source, each of the radio devices 10 receives a broadcasting audio signal from the broadcasting device 30, the determining module 22 defines a first audio signal based on the audio signal from the user received by the radio device 10 for the first time, the radio device 10 receives the audio signal from the broadcasting device 30 next time, the first broadcasting audio signal is defined herein, and the obtaining module 21 obtains a working time axis of the radio device 10 and a working time axis of the broadcasting device 30 based on the first audio signal and the first broadcasting audio signal, respectively. When the determining module 22 determines that a working time axis of the broadcasting device 30 is different from a working time axis of the radio device 10, the broadcasting device adjusting module 27 adjusts the working time axis of the radio device 10 and the working time axis of the broadcasting device 30 to a same working time axis.

The judging module 22 judges whether the broadcasting device 30 and the radio receiving device 10 are not on the same working time axis based on a preset judging program. For example, according to a preset program, the preset time interval from the first time the first audio signal containing the voice command is received by the radio receiver 10 to the time the first broadcast audio signal from the broadcast device 30 is received by the radio receiver 10 is 5 seconds, according to the respective working time axis confidences of the radio reception device 10 and the broadcasting device 30 obtained by the obtaining module 21, it is found that the actual time interval from the first time when the radio reception device 10 receives the first audio signal containing the voice instruction to the time when the radio reception device 10 receives the first broadcasting audio signal from the broadcasting device 30 is 15 seconds, and obviously, a time offset of 10 seconds occurs between the radio reception device 10 and the broadcasting device 30, the working time axis of the radio equipment 10 may be earlier than the broadcasting equipment 3010 seconds, or the working time axis of the radio equipment 10 may be later than the broadcasting equipment 3010 seconds. The adjusting module 23 adjusts the working time axes of the radio receiving device 10 and the broadcasting device 30 to a same time axis, so that an actual time interval from when the radio receiving device 10 receives the first audio signal containing the voice instruction for the first time to when the radio receiving device 10 receives the first broadcasting audio signal from the broadcasting device 30 is 5 seconds.

It is understood that, in some embodiments of the present invention, the radio receiver 10 may be adjusted to a same working time axis according to the audio signal, and then the broadcasting device 30 and the radio receiver 10 may be adjusted to a same working time axis. In other embodiments of the present invention, the radio reception device 10 and the broadcasting device 30 may be directly adjusted to a same operation time axis according to the respective first audio signal and the first broadcasting audio signal. The noise reduction module 25 can perform a noise reduction process on the first audio signal to obtain a noise-reduced first audio signal, which is defined as a second audio signal.

The noise reduction module 25 can also perform noise reduction processing on the first broadcast audio signal to obtain a second broadcast audio signal, the obtaining module 21 obtains work time axis information corresponding to the radio equipment 10 and the broadcast equipment 30 respectively based on the second audio signal of the radio equipment 10 and the second broadcast audio signal of the broadcast equipment 30, and the adjusting module 23 adjusts the radio equipment 10 and the broadcast equipment 30 to the same work time axis according to the work time axis information.

According to another aspect of the present invention, there is provided a vehicle voice processing method, comprising the steps of:

(a) acquiring working time axis information corresponding to each radio equipment 10 according to a first audio signal from the same sound source received by at least two radio equipment 10; and

In a specific example of the vehicle voice processing system 100 of the present invention, the step (b) is implemented as:

if at least one of the working time axes of the radio equipment 10 is different from a standard working time axis, adjusting to the standard working time axis.

confirming a main radio equipment 10 in the radio equipment 10 according to the volume of the audio signal; and

if at least one of the work time axes of other sound receiving equipment 10 is not consistent with the work time axis of the main sound receiving equipment 10, adjusting to be consistent with the work time axis of the main sound receiving equipment 10.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a) is implemented as: according to the receiving time of the same first audio signal received by at least two radio equipments 10, a working time axis information corresponding to each of the radio equipments 10 is obtained.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a) is implemented as: according to the characteristic frequency time of the same first audio signal received by at least two radio equipments 10, obtaining a working time axis information corresponding to each of the radio equipments 10.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a) further includes:

(a.1) at least two radio sets 10 respectively receive a first audio signal; and

(a.2) obtaining a working time axis information corresponding to each of the sound receiving devices 10 when the first audio signals received by each of the sound receiving devices 10 come from the same sound source.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.2) includes:

the first audio signal received at each of the sound receivers 10 is from the same sound source and includes overlapping portions that are separated based on the first audio signal to generate a second audio signal when the first audio signal received for the same sound receiver 10 includes overlapping portions; and

and acquiring working time axis information corresponding to each sound receiving device 10 based on the second audio signal.

the first audio signal received at each of the sound receiving devices 10 is from the same sound source and includes an overlapping portion for the first audio signal received for the same sound receiving device 10, the overlapping portion is separated based on the first audio signal and re-overlapped to generate a second audio signal; and

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a) includes the steps of:

(a.1) at least two radio sets 10 respectively receive a first audio signal;

(a.2) generating a second audio signal based on the first audio signal noise reduction when the first audio signal received for the same radio receiver 10 includes overlapping portions; and

(a.3) obtaining an operation time axis information corresponding to each of the sound receiving devices 10 when the second audio signals corresponding to each of the sound receiving devices 10 come from the same sound source.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.2) is implemented as:

where the first audio signal received for the same radio receiver 10 includes overlapping portions, the overlapping portions are separated based on the first audio signal and re-superimposed to generate a second audio signal. In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.2) is implemented as:

where the first audio signal received for the same radio receiver 10 includes overlapping portions, the overlapping portions are separated based on the first audio signal and re-superimposed to generate a second audio signal.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.3) is implemented as:

the second audio signals corresponding to each of the radio reception devices 10 are from the same sound source, and a working time axis information corresponding to each of the radio reception devices 10 is obtained based on the characteristic frequency time of the second audio signals of different radio reception devices 10.

when the second audio signal corresponding to each of the sound receiving devices 10 comes from the same sound source, an operation time axis information corresponding to each of the sound receiving devices 10 is obtained based on the receiving time of the second audio signal of different sound receiving devices 10.

In a specific example of the vehicle voice processing system 100 of the present invention, further comprising a step (c), wherein the step (c) comprises:

confirming a main radio receiving device 10 and at least one auxiliary radio receiving device 10 according to the first audio signal received by each radio receiving device 10; and

according to a main voice instruction of the first audio signal collected by the main radio equipment 10 and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio equipment 10, determining an execution voice instruction according to the better voice instruction in the main voice instruction and the auxiliary voice instruction, so as to control the vehicle. Said step (c) is located after said step (b).

In a specific example of the vehicle voice processing system 100 of the present invention, the basis for confirming the primary radio device 10 and the secondary radio device 10 in the step (c) is: the volume of the first audio signal, the audio level and the background sound.

confirming a main radio equipment 10 and at least one auxiliary radio equipment 10 according to the volume of the first audio signal received by each radio equipment 10; and

according to a main voice instruction of the first audio signal acquired by the main radio equipment 10 and an auxiliary voice instruction of the first audio signal acquired by the auxiliary radio equipment 10, the main voice instruction and the auxiliary voice instruction are superposed to generate an execution voice instruction for controlling the vehicle.

according to a main voice instruction of the first audio signal collected by the main radio equipment 10 and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio equipment 10, difference processing is carried out on the main voice instruction and the auxiliary voice instruction to generate an execution voice instruction for controlling the vehicle.

according to a main voice instruction of the first audio signal collected by the main radio equipment 10 and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio equipment 10, a segment with good main voice instruction tone quality and a segment with good auxiliary voice instruction tone quality are intercepted to generate an execution voice instruction for controlling the vehicle.

In a specific example of the vehicle voice processing system 100 of the present invention, further comprising a step (d), wherein the step (d) comprises:

(d.1) sending a broadcast voice instruction of the first audio signal collected by the radio equipment 10 to a broadcast equipment 30;

(d.2) acquiring an operation time axis information of the broadcasting equipment 30 based on the reception of a first broadcasting audio signal from the broadcasting equipment 30 by the radio equipment 10 and the reception of the first audio signal by the radio equipment 10; and

(d.3) if the working time axis of the broadcasting equipment 30 is different from the working time axis of the radio equipment 10, adjusting to be the same, wherein the step (d) is positioned after the step (b).

In a specific example of the vehicle voice processing system 100 of the present invention, the step (d.2) is implemented as:

generating a second broadcast audio signal based on the first broadcast audio signal noise reduction when the first broadcast audio signal received for the same broadcast device 30 includes overlapping portions;

when the first audio signal received by the same radio equipment 10 comprises the overlapped part, noise reduction is carried out on the first audio signal to generate a second audio signal; and

and acquiring working time axis information of the broadcasting equipment 30 based on the second broadcasting audio signal of the broadcasting equipment 30 and the second audio signal of the radio equipment 10.

In a specific example of the vehicle voice processing system 100 of the present invention, the time is a time at which the first audio signal is received.

In a specific example of the vehicle voice processing system 100 of the present invention, the time is a time at which a characteristic frequency of the first audio signal is received.

(a.1) noise reduction processing to generate a second audio signal based on the first audio signal when the first audio signal received for the same radio receiver 10 includes overlapping portions; and

(a.2) obtaining a corresponding time based on the second audio signal.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.1) is implemented as: the first audio signal received for the same radio receiver 10 includes overlapping portions that are separated based on the first audio signal to generate a second audio signal.

In a specific example of the vehicle voice processing system 100 of the present invention, the step (a.1) is implemented as:

the first audio signal received for the same radio receiver 10 includes overlapping portions, and is processed in an overlapping manner to generate a second audio signal.

based on a main voice instruction of the first audio signal of the radio equipment 10 and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio equipment 10 which are adjusted to the same time, determining an execution voice instruction according to the better quality of the main voice instruction and the auxiliary voice instruction, so as to control the vehicle.

(d.1) collecting a first broadcast audio signal from a broadcast device 30 based on a broadcast voice command of the first audio signal;

(d.2) acquiring a work time axis information of the broadcasting equipment 30 based on the first broadcasting audio signal and acquiring a work time axis information corresponding to the radio equipment 10 based on the first audio signal, and comparing whether the work time axis of the broadcasting equipment 30 is consistent with the work time axis of each radio equipment 10; and

(d.3) if there is an inconsistency, adjusting to a same working time axis.

when the first broadcast audio signal received by the same radio equipment 10 includes an overlapping part, a second broadcast audio signal is generated by the first broadcast audio signal in a noise reduction processing mode;

when the first audio signal received by the same radio equipment 10 includes an overlapping part, a second audio signal is generated by the first audio signal in a noise reduction processing mode; and

based on the second broadcast audio signal of the radio equipment 10 and the second audio signal of the radio equipment 10, a working time axis information of the broadcast equipment 30 is obtained.

In a specific example of the vehicle voice processing system 100 of the present invention, further comprising step (e), wherein the step (e) comprises the steps of:

acquiring working time axis information corresponding to each radio equipment 10 according to a first audio signal from the same sound source received by at least two radio equipment 10; and

if at least one of the working time axes of the sound receiving devices 10 is different from the others, the working time axes are adjusted to be the same.

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

Claims

1. A vehicle speech processing method, comprising the steps of:

(b) adjusting to a same time at least one of said times of each of said first audio signals being different from others;

further comprising a step (e), wherein the step (e) comprises the steps of:

if at least one of the working time axes of the radio equipment is different from others, adjusting to the same working time axis;

further comprising a step (c), wherein said step (c) comprises:

2. The vehicle voice processing method according to claim 1, wherein the time is a time at which the first audio signal is received.

3. The vehicle voice processing method according to claim 1, wherein the time is a time at which a characteristic frequency of the first audio signal is received.

4. The vehicle voice processing method according to claim 1, wherein the step (a) includes the steps of:

(a.2) obtaining a corresponding time based on the second audio signal.

5. The vehicle voice processing method according to claim 4, wherein the step (a.1) is implemented as:

the first audio signal received for the same radio includes overlapping portions that are separated based on the first audio signal to generate a second audio signal.

6. The vehicle voice processing method according to claim 4, wherein the step (a.1) is implemented as:

7. The vehicle voice processing method according to claim 1, further comprising a step (d), wherein the step (d) comprises:

(d.3) if there is an inconsistency, adjusting to a same working time axis.

8. The vehicle voice processing method according to claim 7, wherein the step (d.2) is implemented as:

9. A vehicle speech processing system, comprising:

at least two radio devices; and

a processing unit, wherein the processing unit and the sound receiving devices are communicably connected to each other, the processing unit acquires times corresponding to the respective first audio signals based on a first audio signal from the same sound source received by the respective sound receiving devices, and adjusts to a same time if at least one of the times of the respective first audio signals is different from the others;

the processing unit comprises an acquisition module, a judgment module and an adjustment module, wherein the acquisition module acquires working time axis information corresponding to each radio device based on each first audio signal, the judgment module judges whether at least one of the working time axes of each radio device is different from others to obtain a judgment result, and the adjustment module processes the working time axis of each radio device according to the judgment result so as to enable the working time axes of each radio device to be consistent;

the processing module is used for processing each adjusted first audio signal to obtain an execution voice instruction;

the processing module comprises a confirming module and a generating module, wherein the confirming module confirms a main radio device and at least one auxiliary radio device according to the first audio signal received by each radio device, the generating module confirms an execution voice instruction according to a main voice instruction of the first audio signal collected by the main radio device and an auxiliary voice instruction of the first audio signal collected by the auxiliary radio device and one of the main voice instruction and the auxiliary voice instruction with better voice quality as the execution voice instruction so as to control the vehicle.

10. The vehicle voice processing system according to claim 9, wherein the processing unit further includes an obtaining module, a judging module, and an adjusting module, wherein the obtaining module obtains times corresponding to the respective first audio signals based on the respective first audio signals, the judging module judges whether at least one of the times of the respective first audio signals is different from others to obtain a judgment result, and the adjusting module processes the times of the respective first audio signals according to the judgment result to make the times of the respective first audio signals consistent.

11. The vehicle voice processing system according to claim 10, further comprising a noise reduction module, wherein the noise reduction module is communicably connected to the sound reception device and the acquisition module, respectively, and if the first audio signal includes an overlapping portion, the noise reduction module performs noise reduction processing on the first audio signal to generate a second audio signal, the acquisition module acquires a time corresponding to each of the second audio signals based on each of the second audio signals, the determination module determines whether at least one of the times of each of the second audio signals is different from others to obtain a determination result, and the adjustment module performs processing on the time of each of the second audio signals according to the determination result to make the times of each of the second audio signals uniform.

12. The vehicle voice processing system according to claim 9, wherein the processing unit further includes a processing module and a broadcast device adjusting module, wherein the processing unit is communicatively connected to the adjusting module, when the processing unit derives a broadcast voice command based on the adjusted first audio signal of each of the radio devices, the radio device receives a first broadcast audio signal from a broadcast device, the obtaining module obtains an operation time axis information of the broadcast device and an operation time axis information corresponding to the radio device based on the first broadcast audio signal, the judging module judges whether the operation time axis of the broadcast device and the operation time axis of each of the radio devices are consistent and derives a judgment result, and the broadcasting equipment adjusting module adjusts the radio equipment and the broadcasting equipment to a same working time axis according to the judgment result.

13. The vehicle voice processing system of claim 10, further comprising a processing module and an announcement device adjustment module, wherein the processing unit is communicatively connected to the adjusting module, when the processing unit derives an announcement speech instruction based on each of the adjusted first audio signals, the radio equipment receives a first broadcast audio signal from broadcast equipment, the acquisition module acquires working time axis information of the broadcast equipment based on the first broadcast audio signal and acquires working time axis information corresponding to the radio equipment from the first audio signal, the judging module judges whether the working time axis of the broadcasting equipment is consistent with the working time axis of each radio equipment or not and obtains a judging result, and the broadcasting equipment adjusting module adjusts the radio equipment and the broadcasting equipment to a same working time axis according to the judgment result.

14. The vehicle voice processing system according to claim 13, further comprising a noise reduction module, wherein the noise reduction module is communicably connected to the broadcasting device and the acquisition module, if the first broadcasting audio signal includes an overlapping portion, the noise reduction module performs noise reduction on the first broadcasting audio signal and the first audio signal to generate a second broadcasting audio signal and a second audio signal, the acquisition module acquires an operation time axis information of the broadcasting device and an operation time axis information corresponding to the radio device based on the second broadcasting audio signal, the determination module determines whether the operation time axis of the broadcasting device and the operation time axis of each of the radio devices are consistent to obtain a determination result, and the broadcasting device adjustment module adjusts the radio device and the broadcasting device to a certain time axis according to the determination result The same working time axis.

15. The vehicle voice processing system according to claim 10, further comprising a recognition module, wherein the recognition module is communicatively connected to the sound receiving device, the recognition module recognizes whether a first audio signal received by the sound receiving device is from the same sound source and derives a recognition result and sends the recognition result to the acquisition module, and the acquisition module acquires the time of the corresponding first audio signal from the same sound source.