In-vehicle call method and device, readable storage medium, electronic equipment and vehicle

Abstract

The invention discloses an in-vehicle call method and device, a readable storage medium, electronic equipment and a vehicle, and relates to the technical field of voice processing, and the method comprises the steps: in response to a received in-vehicle call request, collecting in-vehicle sound signals which comprise a user voice signal and an environment sound signal, the environment sound signal comprises at least one of a media sound signal, a loudspeaker audio signal at a call input position, a howling signal and a noise signal; eliminating an environment sound signal contained in the in-vehicle sound signal to obtain a user voice signal; sound source positioning analysis is carried out on the user voice signal, and a target voice signal input by a riding user corresponding to a call input position is extracted; and determining a call output position corresponding to the in-vehicle call request, and controlling a loudspeaker at the call output position to play the target voice signal according to the target volume. According to the invention, in-vehicle communication can be used with functions of media, navigation and the like at the same time, and user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of voice processing technology, and in particular to an in-vehicle communication method, device, readable storage medium, electronic device and vehicle. Background Art

[0002] In the noisy and complex driving environment, the in-car communication system (ICC) is a key technology to optimize the in-car voice interaction environment. When the driver communicates with the rear passengers, in order to clearly convey the content of the speech, they often lean towards each other or take their eyes off the road and speak louder, which poses a great safety hazard. Therefore, enhancing the voice of the interlocutor and reducing unnecessary noise is of great significance to safe driving.

[0003] Once the ICC system currently configured on many car models is turned on, in order to ensure clear conversation between the front and rear rows, the voice interaction system and media entertainment system in the car need to be turned off. It does not support simultaneous use with media, navigation and other functions, which will seriously affect the user experience. Summary of the invention

[0004] In view of this, the present application provides an in-car call method, device, readable storage medium, electronic device and vehicle, which can solve the technical problem that the current in-car call does not support simultaneous use with media, navigation and other functions, seriously affecting the user experience.

[0005] According to a first aspect of the present application, a method for in-vehicle communication is provided, comprising:

[0006] In response to receiving an in-car call request, collecting an in-car sound signal, the in-car sound signal including a user voice signal and an environmental sound signal, the environmental sound signal including at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal;

[0007] Eliminating the ambient sound signal contained in the in-vehicle sound signal to obtain the user voice signal;

[0008] By performing sound source localization analysis on the user voice signal, a target voice signal recorded by the passenger corresponding to the call input position is extracted;

[0009] Determine a call output position corresponding to the in-vehicle call request, and control a speaker at the call output position to play the target voice signal.

[0010] According to a second aspect of the present application, there is provided an in-vehicle communication device, comprising:

[0011] a processing module, configured to collect in-vehicle sound signals in response to receiving an in-vehicle call request, wherein the in-vehicle sound signals include user voice signals and environmental sound signals, wherein the environmental sound signals include at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal;

[0012] Elimination processing, used to eliminate the ambient sound signal contained in the in-vehicle sound signal to obtain the user voice signal;

[0013] An extraction module is used to extract a target voice signal recorded by a passenger corresponding to a call input position by performing sound source localization analysis on the user voice signal;

[0014] The control module is used to determine the call output position corresponding to the in-vehicle call request and control the speaker at the call output position to play the target voice signal.

[0015] According to a third aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the in-vehicle call method described in the first aspect is implemented.

[0016] According to the fourth aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the computer program, the in-vehicle call method described in the first aspect is implemented.

[0017] According to a fifth aspect of the present application, a vehicle is provided, comprising: the electronic device as described in the fourth aspect.

[0018] By means of the above technical scheme, a method, device, readable storage medium, electronic device and vehicle for in-car calls are provided, which can collect in-car sound signals upon receiving an in-car call request; then eliminate the environmental sound signals contained in the in-car sound signals to obtain user voice signals; further extract the target voice signals recorded by the user in the call input position corresponding to the call input position by performing sound source positioning analysis on the user voice signals; finally, after determining the call output position corresponding to the in-car call request, control the speaker at the call output position to play the target voice signal. The technical scheme disclosed in the present invention can still use the ICC intercom function normally without affecting the use of the in-car voice interaction system and the media entertainment system. When the media, navigation and other functions are carried out simultaneously with the in-car call, by eliminating the environmental sound signals and other voice signals contained in the in-car sound signals, the transmitted call signals can avoid noise, and the conversations in the front and rear rows of the car can be clearly transmitted, so that the user's riding experience is better.

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A schematic diagram of a flow chart of an in-car communication method provided by an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram of a flow chart of an in-car communication method provided by another embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram of the structure of an in-car communication device provided by an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of the structure of an in-car communication device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0027] Currently, the in-car communication system (ICC) configured on many car models, once turned on, requires the voice interaction system and media entertainment system to be turned off to ensure clear conversation between the front and rear rows. It does not support simultaneous use with media, navigation and other functions, which will seriously affect the user experience.

[0028] In order to solve the above technical problems, the present disclosure provides an in-car call method, device, readable storage medium, electronic device and vehicle, which can solve the technical problem that the current in-car call does not support simultaneous use with media, navigation and other functions, seriously affecting the user experience.

[0029] like Figure 1 , an embodiment of the present disclosure provides an in-vehicle call method, comprising:

[0030] Step 101: In response to receiving an in-car call request, collecting in-car sound signals, where the in-car sound signals include user voice signals and environmental sound signals.

[0031] In specific application scenarios, for longer vehicles, such as three-row seat vehicles, when passengers with seats far apart (such as rear passengers and first-row passengers) want to communicate, given the long distance between them, in order to ensure that passengers can hear each other's voice information and ensure the safety of vehicle driving, an ICC system can be deployed in the car, and a sound pickup device (such as a microphone) and a sound playback device (such as a speaker) can be deployed near each passenger. Passenger A can establish a call with another passenger B by creating an in-car call request. When establishing a call, passenger A can pick up voice information through a sound pickup device (such as a microphone) deployed near the seat position, and upload the voice information to the ICC system. The ICC system can extract, denoise, and amplify the voice information, and then send the amplified voice information to a sound playback device (such as a speaker) deployed near the other passenger B, and use the sound playback device to play the voice information recorded by passenger A to passenger B; in addition, many ICC systems currently only support one-way calls and cannot provide full-duplex communication, which seriously affects the user experience. Based on this, by deploying a sound pickup device (such as a microphone) and a sound playback device (such as a speaker) near each passenger, full-duplex communication can be supported to achieve instant chat. Correspondingly, passenger B can also pick up voice information through the sound pickup device (such as a microphone) deployed near the seat position, and send the amplified voice information to the sound playback device (such as a speaker) deployed near passenger A through the ICC system, and use the sound playback device to play the voice information recorded by passenger B to passenger A.

[0032] In order to prevent in-car calls from affecting the use of the in-car voice interaction system and the media entertainment system, the in-car voice interaction system and the media entertainment system may not be turned off during in-car calls. That is, communication between passengers can be established under the premise that the in-car voice interaction system and the media entertainment system are in normal use (i.e., the corresponding audio is being played). However, when the call creator picks up the call voice signal through a sound pickup device (such as a microphone) deployed near the seat position, it may also pick up the audio played by the in-car voice interaction system and the media entertainment system. In this case, the audio constitutes an interference signal of the call voice signal. At this time, the in-car sound signal picked up by the sound pickup device may include both the user voice signal and the ambient sound signal. Among them, the ambient sound signal includes at least one of a media sound signal, a speaker audio signal at the call input position, a howling signal, and a noise signal.

[0033] For example, when a row of passengers and a back row of passengers create an in-car call, the call input position may be the position of a sound pickup device (such as a microphone) deployed near a row of seats in the vehicle, and the speaker audio signal at the call input position may be an audio signal transmitted from other rows of passengers played by a sound playing device (such as a speaker) deployed near the call input position; the howling signal may be a signal transmitted back by other rows of passengers when playing audio signals, such as terminal A playing the sound signal transmitted by terminal B, which is collected again by terminal B and transmitted to terminal A, and played again by terminal A; the noise signal may include noise inside the vehicle, noise outside the vehicle, etc., which are not specifically limited here.

[0034] Step 102: Eliminate the ambient sound signal contained in the in-vehicle sound signal to obtain a user voice signal.

[0035] For the embodiment of the present disclosure, in order to avoid interference of the ambient sound signal with the call voice signal, so that the call voice signal transmitted to the call recipient contains noise, after collecting the in-car sound signal, the ambient sound signal contained in the in-car sound signal can be eliminated to obtain a pure user voice signal.

[0036] Step 103: Perform sound source localization analysis on the user voice signal to extract the target voice signal recorded by the passenger corresponding to the call input position.

[0037] In a specific application scenario, the user voice signal picked up by the sound pickup device deployed by the call creator may include the voice signals of all people in the car, so it is necessary to extract the voice information of the call creator to ensure the accuracy of the call voice signal. Accordingly, for the embodiment of the present disclosure, after obtaining the user voice signal, the user voice signal can be subjected to sound source localization analysis, and the target voice signal recorded by the user corresponding to the call input position can be extracted. Among them, the sound source localization analysis of the user voice signal can be performed based on one or more methods such as relative delay estimation method, beamforming method, signal subspace method, modal domain method, machine learning (or deep learning), etc., which are not specifically limited here.

[0038] In the following embodiment steps of the present disclosure, the sound source localization analysis of the user voice signal based on the beamforming method is taken as an example to illustrate the technical solution in the present disclosure, but it does not constitute a specific limitation. The algorithm usually uses all angle compensation phases for each array element of the array to achieve scanning of the target area, and then weighted sums each signal, and takes the direction with the maximum beam output power as the direction of the target sound source. Common sound source azimuth estimation algorithms based on beamforming include Time Difference of Arrival (TDOA) estimation algorithm, Delay and Sum (DS) algorithm, Minimum Variance Distortionless Response (MVDR) algorithm, Steered Response Power-Phase Transform (SRP-PHAT), etc.

[0039] Step 104: determine a call output position corresponding to the in-car call request, and control the speaker at the call output position to play the target voice signal.

[0040] In a specific application scenario, the in-car call request may include a call input position and a call output position. For the disclosed embodiment, after extracting the target voice signal recorded by the passenger (i.e., the call creator) corresponding to the call input position, the call output position corresponding to the in-car call request is first determined, and the target voice signal is further transmitted to the sound playback device (such as a speaker) at the call output position, and the speaker is used to receive the voice information recorded by the call creator.

[0041] In summary, according to the in-car call method provided by the present application, upon receiving an in-car call request, the in-car sound signal can be collected; then the ambient sound signal contained in the in-car sound signal can be eliminated to obtain the user voice signal; further, by performing sound source positioning analysis on the user voice signal, the target voice signal recorded by the user corresponding to the call input position can be extracted; finally, after determining the call output position corresponding to the in-car call request, the speaker at the call output position is controlled to play the target voice signal. The technical solution disclosed in the present invention can still use the ICC intercom function normally without affecting the use of the in-car voice interaction system and the media entertainment system. When the media, navigation and other functions are carried out simultaneously with the in-car call, by eliminating the ambient sound signal and other voice signals contained in the in-car sound signal, interference with the call signal can be avoided, and clear conversations between the front and rear rows in the car can be achieved, so that the user's riding experience is better.

[0042] Further, as a refinement and extension of the above embodiment, in order to fully illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 2 The specific method shown includes:

[0043] Step 201: In response to receiving an in-car call request, collecting in-car sound signals, where the in-car sound signals include user voice signals and environmental sound signals.

[0044] The environmental sound signal includes at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal.

[0045] For the embodiment of the present disclosure, the specific implementation process can refer to the relevant description in step 101 of the embodiment, which will not be repeated here.

[0046] Step 202: Eliminate the ambient sound signal contained in the in-vehicle sound signal to obtain a user voice signal.

[0047] For the embodiments of the present disclosure, as a possible implementation method, when the ambient sound signal includes at least one of a media sound signal and a speaker audio signal at a call input position, echo cancellation can be performed on the in-vehicle sound signal to eliminate the played media entertainment sound, and eliminate the call sound transmitted from other rows of seats played by the speaker at the call input position. Among them, when performing echo cancellation processing, one or more of the methods such as voice adaptive echo cancellation (Acoustic Echo Cancellation, AEC) algorithm, digital signal processing (Digital Signal Processing, DSP), and machine learning (or deep learning) can be used, and no specific limitation is made here. In the following embodiment steps in the present disclosure, echo cancellation based on machine learning (or deep learning) is taken as an example to illustrate the technical solution in the present disclosure, but it does not constitute a specific limitation. Accordingly, as a possible implementation method, the steps of the embodiment may include: inputting the in-vehicle sound signal into an echo cancellation model, and using the echo cancellation model to perform signal elimination processing on the media sound signal and / or the speaker audio signal, wherein the echo cancellation model is used to extract acoustic features of the in-vehicle sound signal, determine the media sound signal corresponding to the media acoustic features and / or the speaker audio signal corresponding to the speaker acoustic features, and then eliminate the media sound signal and / or the speaker audio signal.

[0048] In a specific application scenario, the echo cancellation model may be any computing model that can perform signal elimination processing on media sound signals and / or speaker audio signals, such as a neural network model, a deep learning model, etc. Exemplarily, the echo cancellation model in the present disclosure may be selected as a hidden Markov model, a conditional random field, and a neural network model, etc., which are not specifically limited here. In a specific application scenario, before executing the steps of this embodiment, the echo cancellation model may also be trained for the task of echo elimination based on a certain number of sample data configured with acoustic feature labels through supervised learning, or unsupervised learning, semi-supervised learning, and reinforcement learning corresponding training methods, until it is determined that the echo cancellation model has reached a convergence state, and it is determined that the echo cancellation model has completed training. Then the trained echo cancellation model can be directly put into the specific application of echo cancellation, that is, the in-vehicle sound signal is input into the echo cancellation model, and the echo cancellation model is used to perform signal elimination processing on the media sound signal and / or the speaker audio signal.

[0049] For the embodiments of the present disclosure, as a possible implementation method, when the ambient sound signal includes a howling signal, the in-vehicle sound signal can be subjected to a howling suppression process to eliminate the howling signal present in the in-vehicle sound signal. Among them, when performing the howling suppression process, one or more methods such as a phase modulation method, a gain control method, and an adaptive feedback cancellation method can be used, which are not specifically limited here. In the following embodiment steps in the present disclosure, the technical solution in the present disclosure is described by taking the use of the phase modulation method for howling suppression as an example, but it does not constitute a specific limitation. Among them, the phase modulation method, in simple terms, is the frequency shift method and the phase shift method. The principle of howling suppression by the frequency shift method and the phase shift method is to move the frequency component of the input signal forward or backward, so that the superposition phenomenon between the input signal and the acoustic feedback signal frequency disappears, or the acoustic feedback phase and the input signal phase are deviated, thereby destroying the phase condition for howling formation, thereby achieving the purpose of suppressing the howling signal. Accordingly, the steps of the embodiment may include: extracting a first howling signal with a fixed frequency from the in-vehicle sound signal; performing signal inversion processing on the first howling signal to obtain a second howling signal after the first howling signal is phase-shifted by 180 degrees; adding the second howling signal to the in-vehicle sound signal, so that the first howling signal and the second howling signal cancel each other out, thereby eliminating the first howling signal contained in the in-vehicle sound signal.

[0050] For the embodiment of the present disclosure, as a possible implementation method, when the ambient sound signal includes a noise signal, the in-vehicle sound signal can be denoised to eliminate the noise signal in the in-vehicle sound signal. Among them, when performing the denoising process, one or more methods such as linear filtering denoising method and Fourier transform denoising can be used, which are not specifically limited here. In the following embodiment steps in the present disclosure, the Fourier transform denoising method is used as an example to illustrate the technical solution in the present disclosure, but it does not constitute a specific limitation. Correspondingly, the embodiment may include: identifying the noise signal contained in the in-vehicle sound signal; removing the noise signal from the in-vehicle sound signal. Among them, when identifying the noise signal contained in the in-vehicle sound signal, the embodiment steps may include: performing a fast Fourier transform on the in-vehicle sound signal to obtain an in-vehicle sound frequency domain signal; obtaining an in-vehicle sound frequency domain signal falling within a preset frequency band range as the frequency domain signal of the target noise, and the preset frequency band range is a frequency band range where the signal amplitude is greater than or equal to the preset amplitude threshold; performing a fast Fourier inverse transform and smoothing process on the frequency domain signal of the target noise to obtain a noise signal.

[0051] Step 203: Based on the microphone array arranged in the car, the user voice signal is divided into beam directions, and the user voice signal with a beam direction corresponding to the sitting direction of the call input position is obtained as the target voice signal recorded by the sitting user corresponding to the call input position.

[0052] The number of array rows of the microphone array may correspond to the number of rows of seats in the vehicle, and the number of array rows of the microphone array may correspond to the number of microphones arranged in each row of seats. To ensure the accuracy of the sound source localization analysis, at least one microphone may be arranged for each seat in each row, and each microphone is used to collect sound wave beams in different preset directions, and the preset direction may be the direction of the seat adjacent to the microphone. Taking a vehicle with three rows of seats, each row containing two seats as an example, the microphone array may be a matrix with 3 array rows and 2 array rows.

[0053] For the embodiments of the present disclosure, when the user voice signal is divided into beam directions based on the microphone array arranged in the car, it can be implemented by one or more of a positioning method based on controllable beamforming of maximum output power, a positioning method based on high-resolution spectrum estimation, a positioning method based on time delay difference of arrival (TDOA) estimation, and a method based on machine learning, which is not specifically limited here. In the following embodiment steps in the present disclosure, the technical solution in the present disclosure is described by taking the use of TDOA for sound source positioning as an example, but it does not constitute a specific limitation. When the sound source is positioned based on TDOA, it is generally divided into two steps: first, the time difference between the sound source signal (user voice signal) reaching the microphone array is calculated; then, the sound source positioning model is established and solved through the geometric shape of the microphone array to obtain the location information of the sound source (positioning estimation), so as to obtain the beam direction division result of the user voice signal. Afterwards, the user voice signal whose beam direction is the sitting direction corresponding to the call input position can be extracted from the beam direction division result as the target voice signal recorded by the user sitting corresponding to the call input position.

[0054] Step 204: compare the volume of the ambient sound signal and the target voice signal, perform volume gain control on the target voice signal, and determine the target volume that the target voice signal needs to reach.

[0055] The target sound volume is greater than the ambient sound volume of the ambient sound signal.

[0056] Given that the voice interaction system and the media entertainment system may be playing audio at the same time when the target voice signal is played, in order to avoid the audio played by the voice interaction system and the media entertainment system being too loud and drowning out the target voice signal, making it impossible for the call recipient to hear the call content clearly, the target volume of the target voice signal can be first determined based on the ambient sound volume of the ambient sound signal, so that the target volume is greater than the ambient sound volume of the ambient sound signal.

[0057] For the embodiments of the present disclosure, specifically by comparing the volume of the ambient sound signal and the target voice signal, when the volume of the ambient sound signal is greater than the volume of the target voice signal, as a possible implementation method, the volume of the ambient sound signal can be reduced based on the attenuation coefficient so that the ambient sound volume is lower than the original volume of the target voice signal. At this time, the original volume is used as the target volume of the target voice signal; as a possible implementation method, the volume of the target voice signal can also be increased based on the enhancement coefficient so that it reaches a target volume greater than the ambient sound.

[0058] Step 205: Control the speaker at the call output position to play the target voice signal at the target volume.

[0059] Given that the voice interaction system and the media entertainment system may be playing audio at the same time when playing the target voice signal, in order to avoid the audio played by the voice interaction system and the media entertainment system being too loud and drowning out the target voice signal, making it impossible for the call receiving user to hear the call content clearly, the speaker at the call output position can be controlled to play the target voice signal at a target volume, wherein the target volume is greater than the ambient sound volume, thereby ensuring that the call receiving user can clearly hear the call content without being affected by noisy ambient sound.

[0060] In summary, according to the in-car call method provided by the present application, upon receiving an in-car call request, the in-car sound signal can be collected; then, the ambient sound signal contained in the in-car sound signal can be eliminated to obtain the user voice signal; further, by performing sound source positioning analysis on the user voice signal, the target voice signal recorded by the user corresponding to the call input position can be extracted; finally, the speaker at the call output position is controlled to play the target voice signal at the target volume. The technical solution disclosed in the present invention can still use the ICC intercom function normally without affecting the use of the in-car voice interaction system and the media entertainment system. When the media, navigation and other functions are carried out simultaneously with the in-car call, the ambient sound signal and other voice signals contained in the in-car sound signal can be eliminated to avoid the presence of noise in the transmitted call signal, so that the conversation between the front and rear rows in the car can be clearly communicated. In addition, after determining the target voice signal recorded by the passenger at the call input position corresponding to the call input position, the target voice signal is controlled by volume gain to ensure that when the speaker at the call output position plays the call sound, the playback volume of the call sound is greater than the ambient sound volume of the ambient sound signal, avoiding the influence of noisy ambient sound, so that the user at the call output position can clearly hear the call content, thereby improving the user's riding experience.

[0061] Based on the above Figure 1 , Figure 2 The specific implementation of the method shown in the embodiment provides an in-car communication device, such as Figure 3 , the device may include:

[0062] The processing module 31 may be used to collect in-vehicle sound signals in response to receiving an in-vehicle call request, where the in-vehicle sound signals include user voice signals and environmental sound signals, where the environmental sound signals include at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal;

[0063] Elimination processing 32, which can be used to eliminate the ambient sound signal contained in the in-car sound signal to obtain the user voice signal;

[0064] The extraction module 33 may be used to extract the target voice signal recorded by the passenger corresponding to the call input position by performing sound source localization analysis on the user voice signal;

[0065] The control module 34 may be used to determine a call output position corresponding to the in-vehicle call request, and control the speaker at the call output position to play a target voice signal.

[0066] In a specific application scenario, when the ambient sound signal includes at least one of a media sound signal and a speaker audio signal at a call input position, the elimination process 32 can be used to input the in-vehicle sound signal into an echo cancellation model, and use the echo cancellation model to perform signal elimination processing on the media sound signal and / or the speaker audio signal, wherein the echo cancellation model is used to extract acoustic features of the in-vehicle sound signal, and after determining the media sound signal corresponding to the media acoustic features and / or the speaker audio signal corresponding to the speaker acoustic features, eliminate the media sound signal and / or the speaker audio signal.

[0067] In a specific application scenario, when the ambient sound signal includes a howling signal, the elimination process 32 can be used to extract a first howling signal with a fixed frequency from the in-vehicle sound signal; perform signal inversion processing on the first howling signal to obtain a second howling signal after the first howling signal is phase-shifted by 180 degrees; perform addition processing on the second howling signal and the in-vehicle sound signal to eliminate the first howling signal contained in the in-vehicle sound signal.

[0068] In a specific application scenario, when the ambient sound signal includes a noise signal, the elimination process 32 can be used to perform a fast Fourier transform on the in-vehicle sound signal to obtain an in-vehicle sound frequency domain signal; obtain an in-vehicle sound frequency domain signal that falls within a preset frequency band as the frequency domain signal of the target noise, and the preset frequency band is a frequency band in which the signal amplitude is greater than or equal to a preset amplitude threshold; perform an inverse fast Fourier transform and smoothing process on the frequency domain signal of the target noise to obtain a noise signal; and remove the noise signal from the in-vehicle sound signal.

[0069] In a specific application scenario, the extraction module 33 can be used to divide the user voice signal into beam directions based on the microphone array arranged in the car, wherein each microphone in the microphone array is used to collect sound wave beams in different preset directions; the user voice signal with a beam direction corresponding to the sitting direction of the call input position is obtained as the target voice signal recorded by the user sitting corresponding to the call input position.

[0070] In specific application scenarios, such as Figure 4 As shown, the device further includes: a comparison module 35;

[0071] The comparison module 35 can be used to compare the volume of the ambient sound signal and the target voice signal, perform volume gain control on the target voice signal, and determine the target volume that the target voice signal needs to reach, wherein the target volume is greater than the ambient sound volume of the ambient sound signal.

[0072] Correspondingly, the control module 34 can be used to control the speaker at the call output position to play the target voice signal according to the target volume.

[0073] It should be noted that for other corresponding descriptions of the functional units involved in the in-car communication device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0074] Based on the above Figure 1 and Figure 2 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.

[0075] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0076] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device that can be configured on the vehicle (such as an electric vehicle) side, and the device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The method shown.

[0077] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0078] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0079] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0080] Based on the above electronic device, the embodiment of the present application further provides a vehicle, which may specifically include: the above electronic device. The vehicle may specifically be an electric car, etc.

[0081] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. The technical solution in the present disclosure can still use the ICC intercom function normally without affecting the use of the in-car voice interaction system and the media entertainment system. When the media, navigation and other functions are carried out simultaneously with the in-car call, by eliminating the ambient sound signal and other voice signals contained in the in-car sound signal, the transmitted call signal is prevented from having noise, and the conversation between the front and rear rows in the car can be clearly communicated. In addition, after determining that the call input position corresponds to the target voice signal recorded by the riding user, by controlling the volume gain of the target voice signal, it can be ensured that when the speaker at the call output position plays the call sound, the playback volume of the call sound is greater than the ambient sound volume of the ambient sound signal, avoiding the influence of noisy ambient sound, so that the user at the call output position can clearly hear the call content, thereby making the user's riding experience better.

[0082] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0083] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A method for in-car communication, characterized in that: include: In response to receiving an in-car call request, collecting an in-car sound signal, the in-car sound signal including a user voice signal and an environmental sound signal, the environmental sound signal including at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal; Eliminating the ambient sound signal contained in the in-vehicle sound signal to obtain the user voice signal; By performing sound source localization analysis on the user voice signal, a target voice signal recorded by the passenger corresponding to the call input position is extracted; Determine a call output position corresponding to the in-vehicle call request, and control a speaker at the call output position to play the target voice signal.

2. The method according to claim 1, characterized in that When the ambient sound signal includes at least one of a media sound signal and a speaker audio signal at a call input position, the step of eliminating the ambient sound signal included in the in-vehicle sound signal includes: The in-vehicle sound signal is input into an echo cancellation model, and the echo cancellation model is used to perform signal elimination processing on the media sound signal and / or the speaker audio signal, wherein the echo cancellation model is used to extract acoustic features of the in-vehicle sound signal, determine the media sound signal corresponding to the media acoustic features and / or the speaker audio signal corresponding to the speaker acoustic features, and then eliminate the media sound signal and / or the speaker audio signal.

3. The method according to claim 1, characterized in that In a case where the ambient sound signal includes a howling signal, the step of eliminating the ambient sound signal included in the in-vehicle sound signal includes: Extracting a first howling signal with a fixed frequency from the in-vehicle sound signal; Performing signal inversion processing on the first howling signal to obtain a second howling signal after the first howling signal is phase-shifted by 180 degrees; The second howling signal and the in-vehicle sound signal are added together to eliminate the first howling signal contained in the in-vehicle sound signal.

4. The method according to claim 1, characterized in that In the case where the ambient sound signal includes a noise signal, the step of eliminating the ambient sound signal included in the in-vehicle sound signal includes: Performing a fast Fourier transform on the in-vehicle sound signal to obtain an in-vehicle sound frequency domain signal; Acquire an in-vehicle sound frequency domain signal falling within a preset frequency band as a frequency domain signal of the target noise, wherein the preset frequency band is a frequency band in which the signal amplitude is greater than or equal to a preset amplitude threshold; Performing inverse fast Fourier transform and smoothing processing on the frequency domain signal of the target noise to obtain a noise signal; The noise signal is removed from the in-vehicle sound signal.

5. The method according to claim 1, characterized in that The method of performing sound source localization analysis on the user voice signal to extract the target voice signal recorded by the user corresponding to the call input position comprises: Based on a microphone array arranged in the vehicle, the user voice signal is divided into beam directions, wherein each microphone in the microphone array is used to collect sound wave beams in different preset directions; A user voice signal whose beam direction is the seating direction corresponding to the call input position is obtained as a target voice signal recorded by the user sitting corresponding to the call input position.

6. The method according to claim 1, characterized in that Before controlling the speaker at the call output position to play the target voice signal according to the target volume, the method further includes: Comparing the volume of the ambient sound signal and the target voice signal, performing volume gain control on the target voice signal, and determining a target volume that the target voice signal needs to reach, wherein the target volume is greater than the ambient sound volume of the ambient sound signal; The controlling the speaker at the call output position to play the target voice signal comprises: The speaker at the call output position is controlled to play the target voice signal according to the target volume.

7. An in-car communication device, characterized in that: include: a processing module, configured to collect in-vehicle sound signals in response to receiving an in-vehicle call request, wherein the in-vehicle sound signals include user voice signals and environmental sound signals, wherein the environmental sound signals include at least one of a media sound signal, a speaker audio signal at a call input position, a howling signal, and a noise signal; Elimination processing, used to eliminate the ambient sound signal contained in the in-vehicle sound signal to obtain the user voice signal; An extraction module is used to extract a target voice signal recorded by a passenger corresponding to a call input position by performing sound source localization analysis on the user voice signal; The control module is used to determine the call output position corresponding to the in-vehicle call request and control the speaker at the call output position to play the target voice signal.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: include: The electronic device as claimed in claim 9.

Images