CN115050382A

CN115050382A - In-vehicle and out-vehicle voice communication method and device, electronic equipment and storage medium

Info

Publication number: CN115050382A
Application number: CN202210656677.5A
Authority: CN
Inventors: 梁爽; 张乐
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2022-06-10
Filing date: 2022-06-10
Publication date: 2022-09-13

Abstract

The embodiment of the invention discloses a method and a device for voice communication between inside and outside of a vehicle, electronic equipment and a storage medium. The in-vehicle and out-vehicle voice communication method comprises the following steps: determining external call main equipment and external call auxiliary equipment according to the positions of external personnel; controlling the external call main equipment to collect alternating current voice and controlling the external call auxiliary equipment to collect environment sound; and reducing the noise of the alternating voice into communication data according to the environment sound, and playing the communication data in the vehicle. According to the embodiment of the invention, the audio signals in the surrounding environment are acquired by the external communication main equipment and the external communication auxiliary equipment, the alternating current signals acquired by the external communication main equipment are reduced into the communication data according to the environment sounds acquired by the external communication auxiliary equipment, so that a good noise reduction effect is achieved, the external communication main equipment and the external communication auxiliary equipment are determined according to the positions of external personnel, the human voice data in the alternating current sounds can be acquired more clearly, the communication quality inside and outside a vehicle is improved, the contact-free communication of an internal partition and an external partition of the vehicle is realized, and the use experience of a user is enhanced.

Description

In-vehicle and out-vehicle voice communication method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of computer application, in particular to a method and a device for voice communication between inside and outside of a vehicle, electronic equipment and a storage medium.

Background

Along with domestic car quantity constantly increases, environmental noise has become the severe problem, and the user requires more and more to the car sound insulation effect, but, sound insulation effect is better and better, separates the window and just more difficult to realize, does not separate the window and exchanges, can not guarantee people's privacy safety.

The communication between the inside and the outside of the vehicle can be realized by respectively arranging microphones inside and outside the vehicle, and when the person in the vehicle needs to communicate with the person outside the vehicle, the microphone can be opened to realize the communication between the isolating window.

However, when the person inside the vehicle communicates with the person outside the vehicle, the communication is not smooth due to the noisy surrounding environment of the vehicle, so a functional way of ensuring effective communication between the person inside the vehicle and the person outside the vehicle in the noisy environment becomes a problem to be solved urgently.

Disclosure of Invention

The invention provides a method and a device for voice communication between the inside and the outside of a vehicle, electronic equipment and a storage medium, which are used for realizing contact-free communication of a partition window, improving the convenience of voice communication between the inside and the outside of the vehicle and enhancing the use experience of a user.

According to an aspect of the present invention, there is provided a method for voice call between inside and outside of a vehicle, wherein the method includes:

determining an external call main device and an external call auxiliary device according to the positions of external personnel;

controlling the external call main equipment to collect alternating current voice and controlling the external call auxiliary equipment to collect environment sound;

and reducing the noise of the alternating current voice into communication data according to the environment sound, and playing the communication data in the vehicle.

According to another aspect of the present invention, there is provided an in-vehicle and out-of-vehicle voice communicator, wherein the communicator comprises:

the acquisition equipment module is used for determining external call main equipment and external call auxiliary equipment according to the positions of external personnel;

the voice acquisition module is used for controlling the external call main equipment to acquire alternating current voice and the external call auxiliary equipment to acquire environmental voice;

and the noise reduction communication module is used for reducing the noise of the communication voice into communication data according to the environment sound and playing the communication data in the vehicle.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the in-vehicle and out-of-vehicle voice call method of any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the in-vehicle and out-of-vehicle voice call method according to any one of the embodiments of the present invention when executed.

According to the technical scheme of the embodiment of the invention, the external call main equipment and the external call auxiliary equipment are determined through the positions of external personnel to acquire the audio signals in the surrounding environment, the external call main equipment acquires the alternating current voice, the external call auxiliary equipment acquires the environment sound, and the alternating current voice is reduced into the call data to be played in the automobile according to the environment sound, so that a good noise reduction effect is achieved, the call quality of the voice call inside and outside the automobile is improved, the contact-free communication of the internal and external partition windows of the automobile is realized, and the use experience of a user is enhanced.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a voice call method between an inside and an outside of a vehicle according to an embodiment of the present invention;

fig. 2 is a flowchart of a car interior and exterior voice communication method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a car interior and exterior voice communication device according to a third embodiment of the present invention;

fig. 4 is an architecture diagram of a car interior and exterior voice communication system according to a fourth embodiment of the present invention;

fig. 5 is a block diagram of a call mode according to a fourth embodiment of the present invention;

FIG. 6 is a block diagram of a pass-through mode according to the fourth embodiment of the present invention;

fig. 7 is a block diagram of a shouting mode provided in accordance with the fourth embodiment of the present invention;

fig. 8 is a schematic structural diagram of an electronic device implementing the in-vehicle and out-of-vehicle voice call method according to the embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of a car interior/exterior voice call method according to an embodiment of the present invention, where the embodiment is applicable to a car interior/exterior voice call situation, and the method may be executed by a voice call device, where the voice call device may be implemented in a form of hardware and/or software, and the voice call device may be configured in a car with a car interior/exterior voice call function. As shown in fig. 1, the method includes:

and S110, determining the main external call equipment and the auxiliary external call equipment according to the positions of the external people.

The position of the external person may include any position around the vehicle, and the positional relationship between the external person and the vehicle may not be limited herein, for example, the external person may be located in front of, behind, or at the side of the vehicle. The external call master device may be a main device for implementing an external call, and may include a sensor having an external sound pickup function, an output device, and the like, for example, a speaker, a sound card, and the like. The sensor with the pickup function outside the vehicle can detect the sound of the surrounding environment outside the vehicle, and the loudspeaker can play the sound signal input in the vehicle. The external call auxiliary device may be a device providing external environment sound, and may include a sensor having an external sound pickup function and a speaker, the sensor having the external sound pickup function may detect external ambient environment sound of the vehicle, and the speaker may play a sound signal input in the vehicle. The number of the external call main devices and the number of the external call auxiliary devices can be one or more, and the installation position can be any position of the external surface of the vehicle, such as four corners of the vehicle, a hood and the like.

Specifically, the mode of confirming the external call main device and the external call auxiliary device can be various, specifically, the position of an external person can be manually selected through a control screen or a button configured in the vehicle, the external call main device can be confirmed according to the position of the external person, and the rest external call devices can be automatically confirmed as the external call auxiliary devices; or the position of the external person can be automatically detected through the sensor, the main external call device can be confirmed according to the position of the external person, and the rest external call devices can be automatically confirmed as the auxiliary external call devices.

In the embodiment of the invention, the main call equipment and the auxiliary call equipment can be confirmed through the positions of external personnel. The position of the external person can be obtained through a manual selection mode of a user or a sensor, and the position of the external person can be specifically selected through a control screen or a button configured in the vehicle by the user; still alternatively, the detection of the person in the vehicle surroundings may be performed using a sensor, and the sensor that detects the position of the person may include a camera, a microphone, a tap sensor, and the like. The main external call device and the auxiliary external call device can be confirmed through the positions of the external persons. The detection of the position of the external person specifically includes using a camera to detect, where the camera may monitor the position of the external person in the surrounding environment based on an image recognition technology, and when an image of the external person is detected, start to confirm the position of the external person; the method comprises the steps that a microphone is used, sound in the surrounding environment can be collected, when the sound of external personnel in the surrounding environment exceeds a volume threshold, the position of the external personnel is confirmed, wherein the volume threshold can be volume set by a user according to requirements or volume set by a vehicle manufacturer according to experience, for example, the volume threshold stored in a vehicle can be 60 decibels, 70 decibels, 90 decibels and the like, and the volume threshold can also be a volume range specifically; the detection is performed by using a knocking sensor, and the knocking sensor can detect vibration or impact generated by knocking a vehicle window, so that the position of an external person is detected. When the positions of the external personnel are confirmed, the external call main equipment and the external call auxiliary equipment can be determined through a deep learning network and the like.

And S120, controlling the external communication main equipment to collect the communication voice and controlling the external communication auxiliary equipment to collect the environment sound.

The communication voice may include human voice and ambient sound, and the ambient sound may refer to sound interfering with the voice call in the ambient environment, such as sound of car whistle, wind sound in the ambient environment, sound interfering with the voice call generated by building construction, transportation, and the like.

Specifically, the external call main equipment and the external call auxiliary equipment can be controlled to be started through the vehicle controller, the alternating-current voice is collected through a sensor in the external call main equipment, and the environment sound is collected through a sensor of the external call auxiliary equipment. The vehicle controller may be implemented by a Micro Controller Unit (MCU) or a System On Chip (SOC).

And S130, reducing the noise of the alternating voice into communication data according to the environment sound, and playing the communication data in the car.

The communication data may be an alternating voice without noise, and may specifically be a clean voice of a person outside the vehicle. The noise reduction mode may be that the ambient sound collected by the external call auxiliary device is used as an ambient sound reference signal, and the communication data is generated by comparing the alternating current voice signal collected by the external call main device with the ambient sound reference signal. The comparison method may specifically include comparing two audio tracks of the ambient sound reference signal and the alternating-current voice signal, deleting the ambient sound, and extracting the call data, or extracting the call data through a neural network module or the like. The playing of the call data can be realized by amplifying weak signals of a sound source or a preamplifier through a power amplifier and pushing sensors such as speakers in the vehicle to play, the number of the speakers can be one or more, and the installation position can be any position in the vehicle, such as the roof, the doors and the like in the vehicle.

Specifically, the communication voice can be denoised into communication data in various ways, the communication voice is denoised according to the environmental sound as a reference signal, the communication data is transmitted to a power amplifier through a controller, the communication data is transmitted to an echo cancellation module through the power amplifier as an echo cancellation reference signal, echo cancellation is carried out through the time difference between the echo cancellation reference signal and the communication data, and finally the communication data after the echo cancellation is played through a loudspeaker. In an exemplary embodiment, the call data may be extracted by comparing the two audio tracks of the ambient sound reference signal and the alternating current voice signal, deleting the ambient sound, or extracting the call data by a neural network module or the like. And transmitting the call data to a power amplifier through a vehicle controller, eliminating echo of the call data, and finally playing the call data in the vehicle through a loudspeaker in the vehicle. Wherein, the communication data can be the voice of the clean outside of the vehicle.

According to the embodiment of the invention, the position of the external person is determined, the external call main equipment and the external call auxiliary equipment are confirmed, so that the external call main equipment can more clearly collect the human voice data in the alternating voice, the alternating voice is collected through the external call main equipment, the external call auxiliary equipment collects the environmental sound, the alternating voice is reduced into the call data to be played in the vehicle according to the environmental sound, the noise is reduced, the call quality of the voice call inside and outside the vehicle is improved, and the use experience of a user is enhanced.

Example two

Fig. 2 is a flowchart of a method for speech communication between inside and outside of a vehicle according to a second embodiment of the present invention, which is embodied on the basis of the above-mentioned embodiments. As shown in fig. 2, the method includes:

and S200, starting a sound sensor and/or an image sensor to acquire multimedia data of external personnel.

The sound sensor can be equipment which receives a sound signal through a microphone, converts the sound signal into an audio signal, determines the change of voltage according to the change of audio frequency and outputs the strength of the sensed sound signal, and is used for collecting the audio signal of external personnel, and the sound sensor can comprise a capacitance sensor, a magnetoelectric sensor and the like; the image sensor may be a device that converts an optical image into an electronic signal for acquiring an image signal of an external person, and may include an analog camera, a digital camera, and the like; the multimedia data is a data set which is large in data volume and includes various types of data, and the multimedia data may include information of external persons collected by a sensor, and the information may include image information, sound information, and the like.

Specifically, the sound sensor and the image sensor can be controlled and started by the vehicle controller to collect external personnel information, the sound sensor can collect audio information of external personnel, and the image sensor can collect image information of external personnel. The collected external person audio information and image information may be stored in the multimedia data. The vehicle controller may be implemented by an MCU or an SOC, for example, a sound sensor and/or an image sensor collects multimedia data of an external person. The number of the sound sensors and the number of the image sensors can be one or more respectively, and the sound sensors and the image sensors can be arranged at any position of the vehicle where the view is not blocked. The collecting of the audio signal by the sound sensor may specifically include detecting by a microphone, which may collect sounds in the environment outside the vehicle, so as to detect sound information of outside persons; capturing an image using the image sensor may specifically include detecting using a camera, which may detect an external person in the environment outside the vehicle based on image recognition techniques.

And S210, extracting the external person position of the external person in the multimedia data.

The manner of extracting the position of the external person from the multimedia data may be, but not limited to, acquiring the position of the external person by recognizing the multimedia data in the vehicle memory, for example. The multimedia data may be stored in a memory of the vehicle, and the outside person position may be extracted by searching the multimedia data stored in the register.

Specifically, the multimedia data stored in the register may be extracted through the MCU or the SOC, and the position of the external person may be determined by searching for image information, sound information, and the like of the external person in the multimedia data.

And S220, determining the position distance between each external communication device and the position of the external person.

The position distance between each external communication device and the external person can be determined in a sensor detection mode, wherein the sensor for detecting the position distance can comprise a radar, an ultrasonic sensor and the like.

Furthermore, each external communication device is respectively installed around the vehicle.

Specifically, the position distances between different external communication devices and the external personnel positions can be detected by adopting different sensors, and the relationship between the direction, the distance and the like between each external communication device and the external personnel positions can be determined by one or more sensors such as a radar sensor, an ultrasonic sensor and the like. For example, the number of the external communication devices may be one or more, and specifically may include 4, 5, and the like. The external communication device can be installed at any position of the vehicle, and specifically can comprise positions around the vehicle, on the roof and the like.

And S230, taking the external communication equipment corresponding to the minimum position distance as external communication main equipment, and taking other external communication equipment as external communication auxiliary equipment.

The location distance may refer to a distance between an external person and an external call device, the minimum location distance may refer to a distance between an external call device closest to the external person and the external person in each external call device, one or more external call devices may be determined as an external call master device by the location distance, the external call device corresponding to the minimum location distance may be used as the external call master device, and the remaining external call devices may be used as external call slave devices.

In the embodiment of the invention, the position distances between each external communication device and the positions of external personnel can be compared, the external communication device corresponding to the minimum position distance is set as the main external communication device through the vehicle controller, and other external communication devices are set as auxiliary external communication devices.

And S240, acquiring the voice call mode input by the user.

The voice call mode may be understood as different types of in-vehicle and out-vehicle voice call modes that can be selected by the user in different scenes. The user can input the voice call mode in different modes, specifically, the voice call mode can be input in a voice mode, a screen touch mode, a button operation mode and the like; the mode of the vehicle for acquiring the voice call mode can be one or more, and the voice call mode can be acquired in different modes according to different modes of the voice call mode input by the user.

Further, the voice call mode includes at least one of: a talk mode, a pass-through mode and a shout mode.

In the embodiment of the invention, the user can trigger different voice call modes of the vehicle in different modes, and the vehicle can acquire the different voice call modes input by the user and control to start the corresponding voice call modes. The user can input the voice call mode in different manners, for example, when the manner in which the user inputs the voice call mode is a voice input manner, the voice call mode can be acquired through a microphone set in the vehicle; when the mode of inputting the voice call mode by the user is screen click operation, the acquisition of the voice call mode can be realized by monitoring the interactive control in the screen. When the mode of inputting the voice call mode by the user is button operation, the voice call mode input by the user can be acquired when the level of the button jumps by monitoring the high and low levels of the button.

S2410, starting the external call main equipment and the external call auxiliary equipment in the call mode, and acquiring the communication voice acquired by the external call main equipment and the environmental sound acquired by the external call auxiliary equipment.

Specifically, the communication mode may be a mode in which the user communicates with a person outside the vehicle without any obstacle. The working mode of the communication mode can be that under the condition that car door window and door are closed, the car can gather the speech data in the environment outside the car and the environment in the car, it makes an uproar to fall the speech data of gathering through the module of making an uproar of falling, and the speech data who will fall the noise transmits for the power amplifier, the power amplifier regards speech data as the interior outer echo cancellation reference signal of car, and transmit to the interior outer echo cancellation module of car, there is a time difference between the interior outer echo cancellation reference signal of car and the speech data of the interior outer noise reduction output of car, rely on this time difference to carry out echo cancellation. The voice data of noise reduction and echo elimination are collected by the voice collecting equipment outside the vehicle which is played by the loudspeaker inside the vehicle, and the voice data of noise reduction and echo elimination are collected by the voice collecting equipment inside the vehicle which is played by the loudspeaker outside the vehicle.

In an exemplary embodiment, in the call mode, the external call main device and the external call auxiliary device may be turned on to collect audio signals in the surrounding environment. The external communication main equipment can collect an alternating current voice signal; the external call auxiliary device can collect the environmental sound signal.

And S2420, in the transparent mode, starting the external call main equipment and the external call auxiliary equipment, and acquiring data collected by the external call main equipment and the external call auxiliary equipment as environmental sound.

In the embodiment of the invention, the transparent mode can be a mode that the tone fidelity of the environment outside the automobile is transmitted to the interior of the automobile for playing, and in the mode, people inside the automobile cannot communicate with people outside the automobile. The working mode of the transparent mode can be that under the condition that the automobile windows and the automobile doors are closed, the automobile can collect voice data in the environment outside the automobile, the collected voice data are transmitted to the power amplifier, and the voice data are played through the sensors such as the loudspeaker in the automobile.

In an exemplary embodiment, in the pass-through mode, the external call master device and the external call slave device may be turned on, and vehicle ambient sound signals collected by the external call master device and the external call slave device may be obtained through the vehicle controller.

And S2430, in the shouting mode, closing the external communication main equipment and the external communication auxiliary equipment.

In the embodiment of the invention, the shouting mode can be a one-way speaking mode in which a person in the vehicle can speak to a person outside the vehicle, and in the mode, the person in the vehicle can not receive a sound signal of the person outside the vehicle. The working method of the shouting mode can be under the condition that car door window and door are closed, the car can gather the speech data that personnel produced in the car, fall and make an uproar through the speech data who falls the module of making an uproar to the collection, and the speech data who falls the noise gives the power amplifier, the power amplifier regards speech data as echo cancellation reference signal in the car, and transmit echo cancellation module in the car, there is a time difference between the speech data of the output of making an uproar of falling in echo cancellation reference signal in the car and the car, rely on this time difference to carry out echo cancellation. And voice data for reducing noise and eliminating echo is collected by the voice collecting equipment in the vehicle through the loudspeaker outside the vehicle.

In an exemplary embodiment, in the shouting mode, the external-call main device and the external-call auxiliary device may be turned off, and no audio signal in the surrounding environment is collected.

And S250, extracting a pre-configured spectrum subtraction processing rule.

The spectral subtraction processing rule may subtract the noise spectrum estimate from the noisy speech estimate to obtain the spectrum of clean speech. In particular, noisy speech may be segmented and windows may be set, a Fast Fourier Transform (FFT) is performed for each window of data, and the magnitude spectrum may be calculated. Voice Activity Detection (VAD) may be used to detect incoming Voice signals. In the non-speech section, the noise spectrum can be estimated and stored in the buffer, and the data in the buffer is attenuated through an algorithm, so that the noise is reduced. In a specific real-time manner, the spectral subtraction processing rule may be configured in a vehicle register, and the preconfigured spectral subtraction processing rule may be extracted through the MCU or the SOC.

And S260, subtracting the environmental sound from the alternating current voice according to a spectral subtraction processing rule to obtain the call data.

Specifically, the noisy speech may be segmented by subtracting the ambient sound noise spectrum from the alternating-current speech collected by the external-call accessory device according to the spectral subtraction processing rule, and set to a window, each data window performs FFT, calculates an amplitude spectrum, and detects the input speech signal by VAD. In the non-voice section, the noise frequency spectrum can be estimated and stored in a buffer area, and then the data in the buffer is attenuated through an algorithm, so that the noise is reduced, namely, the voice is enhanced, the noise is reduced, and the call data is obtained. Wherein the call data may include clean out-of-vehicle voices.

And S270, starting the in-vehicle communication equipment to play the communication data.

The car interior communication equipment can be interior communication equipment, the interior communication equipment can be main equipment for realizing interior communication, the car interior communication equipment can comprise a sensor and a loudspeaker with a car exterior pickup function, the interior communication equipment can be installed at any position without shielding in a car, and the car interior communication equipment can be specifically used for collecting audio signals in the car and playing audio signals input from the outside of the car. The number of intercom devices may be one or more. In one specific embodiment, one or more communication devices in the vehicle can be controlled to be started through the vehicle controller, and communication data generated by noise reduction according to the spectral subtraction processing rule is played.

And S280, only obtaining the environmental sound in a transparent mode, and directly playing the environmental sound in the vehicle.

In a specific embodiment, in the transparent mode, the external call main device and the external call auxiliary device may collect audio signals around the vehicle, where the audio signals are environment sounds, and the environment sounds may be directly played through the in-vehicle call device.

S290, obtaining the environment sound in the vehicle and the human sound in the vehicle in the shouting mode, and playing the human sound in the vehicle based on the noise reduction of the environment sound in the vehicle outside the vehicle.

In one particular embodiment, the intercom devices may be divided into a primary intercom device and a secondary intercom device. The intercom master device may be the primary device implementing the intercom; the intercom auxiliary equipment can gather the interior ambient sound of car, falls the noise to the interior pronunciation of car. Under the mode of shouting, can gather audio signal in the car through intercom main equipment and intercom auxiliary equipment, intercom main equipment gathers speech signal in the car, and intercom auxiliary equipment gathers the ambient sound in the car, subtracts ambient sound as car interior conversation data in will exchanging pronunciation through the spectral subtraction processing rule to broadcast conversation data through the loudspeaker outside the car. The call data may be a noiseless voice.

According to the embodiment of the invention, the position of the external person is extracted by starting the sound sensor and/or the image sensor to collect the multimedia data of the external person, the position relation between the external person and each external communication device is judged to confirm the external communication main device and the external communication auxiliary device, the audio signal of the external person can be collected more clearly, the switching of multiple voice communication modes is achieved by inputting different voice communication modes, the requirements of users in different environments are met, the environment sound is subtracted from the alternating voice to serve as the communication data through the spectrum subtraction processing rule, the good noise reduction effect is achieved, and the quality of the voice communication between the inside and the outside of the vehicle is improved.

Further, on the basis of the above-mentioned embodiment of the invention, the spectral subtraction processing rule includes at least one of: nonlinear spectral subtraction rules, multiband spectral subtraction rules, MMSE spectral subtraction rules, adaptive gain average spectral subtraction rules.

Wherein, the nonlinear spectrum subtraction rule can be that the noise is assumed to have equal influence on all the spectrum components, and then only one over-subtraction factor is used to subtract the over-estimation of the noise; the multi-band spectral subtraction rule may be that in a multi-band algorithm, a speech frequency spectrum is divided into N non-overlapping sub-bands, spectral subtraction operates independently in each sub-band, and a process of dividing a speech signal into a plurality of sub-band signals may be performed by using a band-pass filter in a time domain or using an appropriate window in a frequency domain; MMSE spectral subtraction enables optimal selection of spectral subtraction parameters in the mean square sense; the adaptive gain averaging spectral subtraction rule may be a spectral subtraction rule that divides an analysis frame into smaller sub-frames to obtain a spectrum with a lower resolution, the sub-frame spectrum is continuously averaged to reduce the fluctuation of the spectrum, and the gain function is smoothed over time using adaptive exponential averaging.

EXAMPLE III

Fig. 3 is a schematic structural diagram of a car interior and exterior voice communication device according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: the device comprises an acquisition equipment module 31, a sound acquisition module 32 and a noise reduction conversation module 33.

And the acquisition device module 31 is configured to determine an external call main device and an external call auxiliary device according to the position of the external person.

And the sound collection module 32 is used for controlling the external communication main equipment to collect the alternating-current voice and controlling the external communication auxiliary equipment to collect the environmental sound.

And the noise reduction communication module 33 is used for reducing the noise of the communication voice into communication data according to the environmental sound and playing the communication data in the vehicle.

According to the embodiment of the invention, the position of an external person is determined through the acquisition equipment module so as to confirm the external call main equipment and the external call auxiliary equipment, so that the external call main equipment can more clearly acquire human voice data in the alternating current voice, the external call main equipment is controlled to acquire the alternating current voice through the voice acquisition module, the external call auxiliary equipment acquires environmental voice, the alternating current voice is reduced into call data to be played in the automobile through the noise reduction call module according to the environmental voice, the noise is reduced, the call quality of the in-automobile and out-automobile voice calls is improved, the in-automobile and out-automobile partition window contact-free communication is realized, and the use experience of a user is enhanced.

Further, in the above-described embodiment of the present invention, the acquisition device module 31 includes:

and the sensor starting unit is used for starting the sound sensor and/or the image sensor to acquire the multimedia data of the external personnel.

A position extraction unit for extracting an outside person position of the outside person in the multimedia data.

And the position confirmation unit is used for determining the position distance between each external calling device and the position of the external person, wherein each external calling device is respectively arranged around the vehicle.

And the equipment distribution unit is used for taking the external call equipment corresponding to the minimum position distance as the external call main equipment and taking other external call equipment as the external call auxiliary equipment.

Further, in the above-described embodiment of the invention, the sound collection module 32 includes:

the mode acquisition unit is used for acquiring a voice call mode input by a user, wherein the voice call mode comprises at least one of the following modes: a talk mode, a pass-through mode and a shout mode.

And the first mode working unit is used for starting the external call main equipment and the external call auxiliary equipment in the call mode and acquiring the communication voice acquired by the external call main equipment and the environmental sound acquired by the external call auxiliary equipment.

And the second mode working unit is used for starting the external communication main equipment and the external communication spoke equipment in a transparent mode and acquiring data collected by the external communication main equipment and the external communication auxiliary equipment as environmental sound.

And the third mode working unit is used for closing the external communication main equipment and the external communication auxiliary equipment in the calling mode.

Further, in the above embodiment of the present invention, the noise reduction conversation module 33 includes:

and the rule extraction unit is used for extracting a pre-configured spectral subtraction processing rule. Wherein the spectral subtraction processing rule comprises at least one of: nonlinear spectral subtraction rule, multiband spectral subtraction rule, MMSE spectral subtraction rule, adaptive gain average spectral subtraction rule.

And the call data extraction unit is used for subtracting the environmental sound from the alternating current voice as call data according to the spectral subtraction processing rule.

And the call data playing unit is used for starting the in-vehicle call equipment to play the call data.

Further, on the basis of the above embodiment of the present invention, the in-vehicle and outside voice communication apparatus further includes:

and the environment sound playing unit is used for only obtaining the environment sound in the transparent mode and then directly playing the environment sound in the vehicle.

and the voice playing unit is used for acquiring the environment voice in the vehicle and the voice in the vehicle in the shouting mode, and playing the voice in the vehicle based on the noise reduction of the environment voice in the vehicle outside the vehicle.

The in-vehicle and outside voice communication device provided by the embodiment of the invention can execute the in-vehicle and outside voice communication method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

Example four

Fig. 4 is an architecture diagram of a car interior and exterior voice communication system according to a fourth embodiment of the present invention. The present embodiment is a specific example based on the above-described embodiments. As shown in fig. 4, the system includes: an exterior microphone 41, an interior microphone 42, a cabin controller 43, a power amplifier 44, an exterior speaker 45, and an interior speaker 46.

The outer microphone 41 of the vehicle can form a vehicle outer microphone matrix, the vehicle outer microphone matrix comprises at least four vehicle outer microphones, and the positions of the vehicle outer microphones can be set to be at least one in front, back, left and right, so that the functions of vehicle outer pickup and vehicle outer pickup noise reduction are realized.

The in-car microphone 42 is used for collecting the sound produced by the in-car user, and after noise reduction and echo elimination, the signal is transmitted to a power amplifier and finally played by a loudspeaker outside the car.

The cabin controller 43 may be implemented by an SOC, which is a system or product formed by combining a plurality of integrated circuits with specific functions on one chip, and includes a complete hardware system and embedded software carried by the hardware system, and is a chip at the core of the infotainment system. The SOC integrates an external noise reduction echo elimination algorithm and an internal noise reduction echo elimination algorithm, and two relatively independent software modules are responsible for the inside and the outside of the vehicle.

The power amplifier 44 is used to amplify the weak signal from the sound source or the preamplifier to drive the loudspeaker to play sound.

The loudspeaker 45 outside the vehicle is used for converting the power amplifier transmission electric signal into an acoustic signal to be played outside the vehicle.

The speaker 46 is used to convert the electric signal transmitted by the power amplifier into an acoustic signal for playing in the vehicle.

According to the actual requirements of users, a communication mode, a transparent mode and a shouting mode can be selected, and communication channels inside and outside the vehicle can be closed. Fig. 5 is a block diagram of a call mode according to a fourth embodiment of the present invention.

And 11, selecting the position of a person to be communicated from the control screen by a user in the automobile, and selecting the position corresponding to the arrangement position of the external microphone to at least meet four directions of front, back, left and right.

And step 12, after the user selects a certain position, the external microphone at the corresponding position serves as an external Microphone (MIC) 1 of the external main pickup microphone and is used for collecting external pickup signals.

And step 13, selecting other external MICs 2-4 except the microphone by a user as environmental sound reference signals for noise reduction of the sound outside the vehicle, and acquiring the environmental reference signals outside the vehicle by the external MIC 2-4.

And step 14, collecting pickup signals in the automobile by the internal MIC.

And step 15, inputting the outside pickup signal collected by the outside MIC1 and the outside environment reference signal collected by the outside MIC2-4 into an outside noise reduction/echo cancellation module, comparing the outside pickup signal collected by the outside MIC1 with the environment sound reference signal collected by the MIC2-4, and generating the outside pure human voice to be transmitted to the power amplifier.

And step 16, inputting the in-vehicle pickup signal acquired by the internal MIC into an internal noise reduction/echo cancellation module, comparing the in-vehicle pickup signal with environmental sound, generating in-vehicle pure voice and transmitting the in-vehicle pure voice to a power amplifier.

And step 17, the power amplifier transmits the pure voice outside the automobile to the external noise reduction/echo cancellation module as an echo cancellation reference signal outside the automobile, a time difference exists between the echo cancellation reference signal and the pure voice output by the external noise reduction/echo cancellation module, and echo cancellation is carried out according to the time difference.

And step 18, the power amplifier transmits the pure voice in the vehicle as an in-vehicle echo cancellation reference signal to the internal noise reduction/echo cancellation module, a time difference exists between the in-vehicle echo cancellation reference signal and the pure voice output by the internal noise reduction/echo cancellation, and echo cancellation is carried out according to the time difference.

Step 19, amplifying the pure voice weak signal outside the vehicle after the echo is eliminated by the external noise reduction/echo elimination module through a power amplifier, and transmitting the amplified signal to an internal loudspeaker for playing; and amplifying the pure human voice weak signal in the vehicle after the echo is eliminated by the internal noise reduction/echo elimination module through a power amplifier, and transmitting the amplified pure human voice weak signal to an external loudspeaker for playing.

According to the embodiment of the invention, the communication mode can realize communication between the inside and the outside of the automobile, and is used for communication scenes between the inside and the outside of the automobile. No matter what position the target is outside can realize, fine noise reduction effect can be realized to the homoenergetic, promotes the inside and outside speech quality of car.

Fig. 6 is a block diagram of a pass-through mode according to a fourth embodiment of the present invention.

And step 21, collecting complete environment sounds outside the vehicle by using an external MIC 1-4.

And step 22, transmitting the complete environment sound outside the vehicle in the power amplifier to an internal noise reduction/echo elimination module, wherein the algorithm of the internal noise reduction/echo elimination module does not work, and signals are transmitted through.

And step 23, transmitting the complete environment sound outside the vehicle of the external noise reduction/echo cancellation module to a power amplifier.

And 24, amplifying the external complete environment sound weak signal from the external noise reduction/echo cancellation module through a power amplifier, and transmitting the amplified external complete environment sound weak signal to an internal loudspeaker for playing.

In the embodiment of the invention, the transparent mode can perfectly repeat the external environment sound to the interior of the vehicle under the scene that the door and the window are closed, is used for the scene that the whole external sound needs to be heard in detail, and is generally used for listening to the natural sound when people go out for playing. At the moment, the in-vehicle microphone signal is not sent to the power amplifier, and the out-vehicle noise reduction module does not work.

Fig. 7 is a block diagram of a shouting mode according to a fourth embodiment of the present invention.

And step 31, collecting pickup signals in the automobile by the internal MIC.

Step 32, inputting the pickup signal outside the vehicle collected by the internal MIC into the internal noise reduction/echo cancellation module, comparing the pickup signal inside the vehicle with the environmental sound, generating pure voice and transmitting the voice to the power amplifier.

And step 33, the power amplifier transmits the pure voice as an in-vehicle echo cancellation reference signal to the internal noise reduction/echo cancellation module, a time difference exists between the in-vehicle echo cancellation reference signal and the pure voice output by the internal noise reduction/echo cancellation, and echo cancellation is performed according to the time difference.

And step 34, amplifying the pure human sound weak signal from the internal noise reduction/echo cancellation module after the echo is cancelled by the power amplifier, and transmitting the amplified pure human sound weak signal to an external loudspeaker for playing.

According to the embodiment of the invention, in the shouting mode, members in a vehicle can shout to the outside of the vehicle under the closed scene of a vehicle door and a vehicle window, the shout is generally used for warning, and at the moment, a microphone pickup signal outside the vehicle is not sent to a power amplifier.

EXAMPLE five

FIG. 8 illustrates a block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the in-vehicle and out-of-vehicle voice call method.

In some embodiments, the in-vehicle and out-of-vehicle voice call method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the in-vehicle and out-of-vehicle voice call method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the in-vehicle and out-of-vehicle voice call method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A voice communication method between the inside and the outside of a vehicle is characterized by comprising the following steps: determining external call main equipment and external call auxiliary equipment according to the positions of external personnel;

controlling the external communication main equipment to collect alternating current voice and the external communication auxiliary equipment to collect environment sound;

and denoising the alternating current voice into communication data according to the environment sound, and playing the communication data in the vehicle.

2. The method of claim 1, wherein the determining the external call primary device and the external call secondary device according to the external person position comprises:

starting a sound sensor and/or an image sensor to acquire multimedia data of the external personnel;

extracting an external person position of the external person in the multimedia data;

determining the position distance between each external communication device and the position of the external personnel, wherein each external communication device is respectively arranged around the vehicle;

and taking the external communication equipment corresponding to the minimum position distance as the external communication main equipment, and taking other external communication equipment as the external communication auxiliary equipment.

3. The method according to claim 1, wherein the controlling the main external call device to collect the communication voice and the auxiliary external call device to collect the environmental sound comprises:

acquiring a voice call mode input by a user, wherein the voice call mode comprises at least one of the following modes: a talk mode, a pass-through mode and a shout mode;

in the call mode, starting the external call main equipment and the external call auxiliary equipment, and acquiring the alternating current voice collected by the external call main equipment and the environment sound collected by the external call auxiliary equipment;

in the transparent mode, starting the external call main equipment and the external call auxiliary equipment, and acquiring data collected by the external call main equipment and the external call auxiliary equipment as the environmental sound;

and in the shouting mode, closing the main external communication equipment and the auxiliary external communication equipment.

4. The method according to claim 1 or 3, wherein the reducing the alternating current voice into the call data according to the environmental sound and playing the call data in the vehicle comprises:

extracting a pre-configured spectral subtraction processing rule;

subtracting the environmental sound from the alternating current voice according to the spectral subtraction processing rule to obtain the communication data;

and starting the in-vehicle communication equipment to play the communication data.

5. The method of claim 4, wherein the spectral subtraction processing rule comprises at least one of: nonlinear spectral subtraction rules, multiband spectral subtraction rules, MMSE spectral subtraction rules, adaptive gain average spectral subtraction rules.

6. The method of claim 1 or 3, further comprising:

and only acquiring the environment sound in the transparent mode, and directly playing the environment sound in the vehicle.

7. The method of claim 1 or 3, further comprising:

the method comprises the steps of obtaining environment sound in the vehicle and the voice in the vehicle in the shouting mode, and playing the voice in the vehicle based on noise reduction of the environment sound in the vehicle outside the vehicle.

8. An in-vehicle and out-vehicle voice communication apparatus, characterized in that the apparatus comprises:

the sound collection module is used for controlling the external communication main equipment to collect alternating current voice and the external communication auxiliary equipment to collect environmental sound;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the in-vehicle and out-of-vehicle voice call method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions for causing a processor to implement the in-vehicle voice call method according to any one of claims 1 to 7 when executed.