Vehicle-mounted call voice processing method and system, electronic equipment and storage medium

Abstract

The invention relates to the technical field of voice processing, discloses a vehicle-mounted call voice processing method and system, electronic equipment and a storage medium, and aims to solve the problems that an existing vehicle-mounted communication system is poor in privacy and low in call quality. Selecting a target playing device of the call audio from the playing devices in the vehicle, and controlling the target playing device to play the call audio; if the current vehicle-mounted call mode is the private call mode, acquiring a current call encryption level; according to the current conversation encryption level, the second playing device is controlled to play the content matched with the encryption level, privacy conversation protection is achieved, interference noise is effectively removed, in-vehicle conversation privacy is protected, and through aliasing reconstruction of conversation audio and music, the driving experience is improved, and the privacy and safety of communication are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of voice processing technology, and in particular to a method, system, electronic device and storage medium for in-vehicle call voice processing. Background Art

[0002] With the development of automobile technology and the improvement of people's living standards, more and more families own private cars, and the vehicle communication system is one of the important components of modern cars. However, while the existing technology provides convenience, it also has some defects.

[0003] 1. When making calls in the car, the noise in the car, such as engine roar, wind noise, etc., may interfere with the call quality, causing the call quality to deteriorate; 2. Other passengers in the car will hear the conversation, which may leak the privacy of both parties; 3. During a call, the in-car navigation, music, etc. will be interrupted, affecting the riding experience of other people in the car.

[0004] Therefore, it is necessary to provide a new in-vehicle call voice processing method to achieve the noise reduction effect during in-vehicle calls, protect the privacy in the car, improve the call quality, and enhance the driving experience. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method, system, electronic device and storage medium for in-vehicle call voice processing, which can achieve noise reduction effect during in-vehicle calls, protect privacy in the car, improve call quality, and enhance the driving experience.

[0006] In a first aspect, the present invention provides a method for processing vehicle-mounted call voice, comprising: When the in-vehicle call is connected, obtaining the current in-vehicle call mode; the in-vehicle call mode includes a non-privacy call mode and a privacy call mode; According to the current in-vehicle call mode, a target playback device for the call audio is selected from the playback devices in the vehicle, and the target playback device is controlled to play the call audio; wherein the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person who is talking in the vehicle is smaller than the distance between the second playback device and the person who is talking in the vehicle; If the current in-car call mode is the private call mode, obtain the current call encryption level; According to the current call encryption level, controlling the second playback device to play content matching the encryption level; According to the current in-vehicle call mode, a target playback device for the call audio is selected from the playback devices in the vehicle, in the following method: If the current in-vehicle call mode is a private call mode, using a first playback device to play the call audio; When the current in-vehicle call mode is a non-privacy call mode, the call audio is played using the first playback device and / or the second playback device.

[0007] In a second aspect, the present invention provides a vehicle-mounted call voice processing system, which adopts the vehicle-mounted call voice processing method as described in any one of the above items, and specifically includes: Audio receiving device: used to receive mixed audio; Audio processing module: used to obtain the current in-vehicle call mode when the in-vehicle call is connected; the in-vehicle call mode includes a non-privacy call mode and a privacy call mode; according to the current in-vehicle call mode, select a target playback device for the call audio from the playback devices in the car, and control the target playback device to play the call audio; if the current in-vehicle call mode is a privacy call mode, obtain the current call encryption level; according to the current call encryption level, control the second playback device to play content matching the encryption level; Playback device: used for playing audio; the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person talking in the car is smaller than the distance between the second playback device and the person talking in the car.

[0008] In a third aspect, the present invention provides an electronic device, the electronic device comprising: Processor and memory; The processor is used to execute the steps of the in-vehicle call voice processing method as described in any one of the above items by calling the program or instruction stored in the memory.

[0009] In a fourth aspect, the present invention provides a storage medium, characterized in that the storage medium stores a computer executable program, which is called by a processor to execute the steps of any of the above-mentioned in-vehicle call voice processing methods.

[0010] The embodiments of the present invention have the following technical effects: First, the privacy call mode: the present invention selects a target playback device for the call audio from the playback devices in the car according to the current in-car call mode. In the privacy mode, the system only plays the audio of the call content on the playback device closer to the caller, preventing the voices of other people in the car from being heard by the caller, thereby enhancing the privacy of the communication; Second, intelligent matching of encryption level and playback mode: According to the different encryption levels, the system can intelligently adjust the audio output of other playback devices. Entertainment audio is played under level 1 encryption, while interference audio is played under level 2 encryption, further enhancing the privacy and security of calls. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 is a flow chart of a vehicle call voice processing method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a vehicle call voice processing system provided by an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0014] The specific implementation of the present invention is described below with reference to the accompanying drawings.

[0015] The present invention aims to solve the problems of poor privacy and low call quality in existing in-vehicle communication systems. The present invention obtains the current in-vehicle call mode, selects a target playback device for the call audio from the playback devices in the car according to the current in-vehicle call mode, and controls the target playback device to play the call audio; if the current in-vehicle call mode is a privacy call mode, obtains the current call encryption level; according to the current call encryption level, controls the second playback device to play content matching the encryption level, thereby realizing privacy call protection, effectively removing interfering noise, protecting the privacy of in-vehicle calls, and improving the driving experience and enhancing the privacy and security of communications through aliasing reconstruction of call audio and music.

[0016] Example 1 The present invention proposes a vehicle-mounted call voice processing method. Figure 1 is a flow chart of a vehicle call voice processing method provided by an embodiment of the present invention, see Figure 1 , including steps S1 to S4: Step S1, when the in-vehicle call is connected, obtain the current in-vehicle call mode; the in-vehicle call mode includes a non-privacy call mode and a privacy call mode.

[0017] The in-car call modes can be divided into encrypted and non-encrypted modes to meet different call needs and help improve the driving experience.

[0018] Non-private call mode: The call content can be heard by all passengers in the car, which is suitable for ordinary call scenarios that do not require confidentiality. When this mode is selected, the system may play the call audio on all or specified playback devices in the car.

[0019] Private call mode: When the content of the call needs to be kept confidential, or there are other passengers in the car and the caller does not want the call to be heard by others, you can select the private call mode. In this mode, the system will limit the playback range of the call audio, usually only playing it on one or several playback devices closest to the caller, to reduce the possibility of the call content being heard by others.

[0020] Step S2, according to the current in-vehicle call mode, select a target playback device for the call audio from the playback devices in the car, and control the target playback device to play the call audio; wherein the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person talking in the car is smaller than the distance between the second playback device and the person talking in the car.

[0021] Furthermore, according to the current in-car call mode, a target playback device for the call audio is selected from the playback devices in the car, and the method is: If the current in-car call mode is a private call mode, using the first playback device to play the call audio can reduce the possibility that the call content can be heard by other passengers in the car; When the current in-vehicle call mode is a non-private call mode, the call audio is played using the first playback device and / or the second playback device, and it is selected as needed whether to allow all passengers to hear the call content.

[0022] Through sound source positioning, such as the array microphone and image sensor in the car, the position of the voice call object in the car is determined, and then the distance between each playback device in the car and the caller is determined. According to the needs of the caller, the playback device is divided into the first playback device and the second playback device. The system can dynamically adjust the playback device's capabilities and adjust the playback strategy in real time according to changes during the call (such as passenger movement, door opening and closing, etc.).

[0023] The playback device is divided into a first playback device and a second playback device, where the first playback device is usually located closer to the caller, while the second playback device is located farther away. This helps to limit the call audio to be played near the caller in the private call mode, so as to reduce interference to other passengers and the risk of privacy leakage.

[0024] Furthermore, before controlling the target playback device to play the call audio, the volume of the playback device is adjusted according to the caller's emotions, call keywords, and response level, specifically: Acquire the emotions of the caller through the voice emotion recognition model; Use neural network model to model conversation keywords and response level; Adjust the volume of the playback device according to the caller's mood, call keywords and response level.

[0025] Furthermore, before controlling the target playback device to play the call audio, it also includes: performing call audio extraction processing on the transmitted mixed audio, and performing aliasing reconstruction processing on the call audio after the call audio extraction processing.

[0026] Before playing the call audio, the mixed audio is first processed for call audio extraction, including noise reduction, voice separation, keyword recognition, and voiceprint feature extraction, aiming to accurately extract the caller's voice from the mixed audio. In non-privacy mode, aliasing reconstruction is performed to merge the extracted call audio with the original audio in the car (such as music or navigation sound) to achieve simultaneous playback of the call content and the original audio in the car.

[0027] Aliasing reconstruction processing ensures the harmonious unity of call audio and the ambient audio in the car, improves the clarity and privacy of calls, while avoiding unnecessary interference to other passengers in the car, thereby optimizing the overall driving experience.

[0028] Specifically, the mixed audio extraction process includes steps S21-S25: Step S21, performing noise reduction processing on the mixed audio; Step S22, separating the human voice audio from the mixed audio after the noise reduction process; Step S23, performing keyword recognition on the human voice audio, and retaining sentence audio containing the voice call keywords; Step S24, performing voiceprint feature recognition on the sentence audio containing the voice call keywords, and outputting the voiceprint features of the caller; Step S25: extracting the call audio according to the voiceprint feature.

[0029] Through the call audio extraction processing of steps S21 to S25, the voice of the target caller can be accurately extracted from the complex in-vehicle audio environment, which not only improves the call quality and ensures the clarity and intelligibility of the voice, but also enhances the security and privacy of the call through the matching of voiceprint features, making the call experience smoother and more focused.

[0030] If the audio is mixed with broadcast sounds, car horns and other people's chatting sounds, then step S21 is used to obtain audio with reduced background noise, step S22 is used to obtain audio containing only human voices, step S23 is used to obtain sentence audio containing call keywords, such as audio containing "hello", "hello", "where are you", etc., step S24 is used to obtain the voiceprint features of the callers, and step S25 is used to obtain all the audio of the callers in the audio.

[0031] In the present invention, the call audio is not directly extracted from the mixed audio. This is because not every sentence spoken by the caller may contain the call keywords. In order to avoid the system missing part of the call audio, the present invention reduces the background noise through noise reduction processing, and then separates the human voice part, and then identifies the keywords to locate the call audio, and obtains the voiceprint features of the caller through voiceprint recognition technology. In this way, the audio is subsequently extracted according to the voiceprint features, and finally the complete and clear voice of the specific caller is extracted.

[0032] The method of separating the human voice audio from the mixed audio after the noise reduction process comprises: Input the noise-reduced mixed audio into the trained separation model and output the human voice audio; The separation model is used to extract human voice audio from a variety of mixed audios, and existing methods for achieving sound separation in the prior art can be used in the present invention.

[0033] The aliasing reconstruction process is performed on the call audio after the call audio extraction process, specifically: The call audio extracted and processed by the call audio is reconstructed by aliasing with the audio being played in the car before the in-car call is turned on, and the aliased and reconstructed audio is then played through the target playback device.

[0034] Aliasing reconstruction is an advanced audio processing technology that involves intelligently blending the processed call audio with the original audio content in the car, such as music, navigation instructions, or other media audio. This process ensures the natural transition and smoothness of the call audio while minimizing interference to other passengers in the car. With this technology, the audio experience in the car remains coherent and pleasant even during a call, and the transition between the call content and the background audio becomes smooth, thereby improving the overall auditory comfort and call quality. In addition, aliasing reconstruction also helps to achieve shared audio playback in non-privacy call mode, or limit the call audio to a specific area in privacy mode, ensuring the privacy of the call and the auditory enjoyment of the passengers.

[0035] Furthermore, the sound categories contained in the mixed audio can be distinguished and processed differently.

[0036] (1) If the picked-up audio is pure music (or other audio that does not contain human voice), it is not difficult for the user to recognize the voice of the caller after reconstructing the music and the call. The frequency range and sound intensity of the human voice can be enhanced through sound enhancement technology (digital signal processing technology) to make the human voice clearer than the audio. Or noise suppression technology can analyze the characteristics of background noise and use filtering, compensation and other technologies to eliminate echo interference and improve the clarity of the human voice. Or audio coding technology can compress and decode audio data to reduce the size of audio files and improve the playback speed and sound quality. Or microphone array technology can achieve directional collection and positioning of human voice through an array composed of multiple microphones, thereby improving the clarity of human voice. (2) If the picked-up audio contains human voice, then according to the above-mentioned converted text, the caller's emotion, speaking speed, keywords in the call content, and the user's response level are identified based on the call text information to make corresponding decisions, such as whether to stop playing the in-car audio or reduce the volume of the in-car audio or enhance the noise reduction function of the in-car audio to make the human voice clear, so that the user can better obtain call information and improve call quality; Identifying the emotions of the caller is done through speech emotion recognition technology: first, a certain amount of speech data needs to be collected, including speech data in different emotional states, such as happiness, sadness, anger, etc.; feature extraction is performed on the collected speech data, and the speech signal is converted into a set of numerical features, such as fundamental frequency, energy, harmonics, etc.; the extracted features are trained using machine learning algorithms or deep learning models to establish an emotion classification model; emotion classification is performed on new speech data, and it is classified into different emotion types; different emotion types can also be prioritized or graded, and the system performs adaptive in-car audio adjustments based on the priorities or levels of different emotions; Keywords during calls are also collected by collecting the target user's daily call content, using databases and data training to determine the target user's attention and interest in different call contents, so as to extract the keywords in the corresponding sentences and save them; compare keywords in new conversations, classify them into different priorities and importance levels to adaptively adjust the in-car audio; The user's responsiveness refers to the degree of the user's response to the content of the call, including the number of replies, reply duration, speaking frequency, duration, etc. It is used to measure whether the user is interested in the call or wants to answer it, and to determine whether the in-car audio needs to be adjusted to improve the call quality.

[0037] In addition to the above processing of call audio, the present invention can also be used to perform the above processing on the audio in the vehicle. During a call, the system automatically picks up the audio in the vehicle, performs the above call audio extraction processing on the audio in the vehicle, obtains the call audio in the vehicle, and only transmits the call audio in the vehicle to the other party, thereby protecting the privacy in the vehicle.

[0038] The microphone picks up the sounds in the car, such as audio and calls, and then identifies their digital signals. The digital audio signals of music are usually transmitted from music files (MP3, WAV and other formats) or network streaming media, and usually have higher sampling rates, bit depths and number of channels, etc., to ensure the details and quality of the music; while the digital audio signals when making calls are generated by the telephone communication system, and usually have lower sampling rates and bit depths, etc., to save bandwidth and storage space, and to ensure the fluency and intelligibility of the voice; the difference in the above digital signals is used to distinguish between call and audio signals when picking up the sound.

[0039] Step S3, if the current in-vehicle call mode is a private call mode, obtain the current call encryption level; Step S4: According to the current call encryption level, control the second playback device to play content matching the encryption level.

[0040] When the current call encryption level is level one, controlling the second playback device to play entertainment audio; When the current call encryption level is level 2, controlling the second playback device to play interference audio; The interference audio is entertainment audio whose voiceprint features are consistent with the voiceprint features of the caller.

[0041] The caller selects the encryption level for the call as needed. Encryption level control is a privacy protection mechanism that determines the content played by the second playback device (farther away from the caller) based on the sensitivity of the call. In the first level of encryption, ordinary entertainment audio is played, which is suitable for scenarios where the content of the call does not involve privacy; in the second level of encryption, interference audio consistent with the caller's voiceprint characteristics is played. This interference audio can effectively cover up the content of the call and is suitable for calls that require higher privacy protection. This design not only ensures the privacy of the call, but also provides different levels of privacy options to meet different call needs.

[0042] The audio playback device reconstructs the call audio and the pure audio information in the car to obtain a new mixed audio signal, while highlighting the vocal signal of the call partner, and uses the audio signal for the in-car call audio.

[0043] Furthermore, the new mixed audio signal can be played on the first playback device, while the playback devices in other areas continue to play normally, which ensures that the call party can receive clear call voice audio, and also ensures that the audio-visual experience of non-call party passengers is not interrupted by the call or causes discomfort due to the call.

[0044] When the call privacy mode is turned on, the microphone picks up the audio of the non-calling party in the car, extracts the audio features, and uses them for active noise reduction or voice masking in the car area. By playing or reducing the audio or voice masking the audio on the playback device in the target area, the non-calling party in the car cannot obtain the accurate voice and audio information of the calling party. At the same time, since voiceprint recognition and tracking are turned on, the in-car call microphone will not pick up other audio signals of the non-calling party in the car. This ensures that the content of the call cannot be heard by other passengers in the car, and the conversations or entertainment audio of other passengers in the car will not be obtained by the calling party outside the car, thus ensuring the privacy of the call.

[0045] Audio mixing technology is used to mix multiple different audio signals into a new audio signal in a certain proportion. The volume, balance and frequency characteristic parameters of the signals are adjusted according to the characteristics of the audio signals and call signals to ensure coordination between the various signals. In the later stage, equalizers, compressors, reverberators, etc. can be added as needed to enhance the expressiveness of the audio signal, or post-processing such as noise reduction, denoising, gain control, etc. can be performed to improve the audio quality and effect.

[0046] In non-privacy call mode, the present invention reconstructs the audio of the call content by mixing it with the audio played in the car, thereby achieving simultaneous playback of call audio and music. This can make the call sound more naturally integrated into the car environment, improve the driving experience, and ensure the clarity of the call content and the enjoyment of the music.

[0047] Furthermore, emotion recognition processing can be added to the in-vehicle call processing method of the present invention. Through audio features, voice emotion recognition can be performed on the current object, and different in-vehicle control parameters can be preset according to different emotional states. For example, the call volume, entertainment audio playback volume, air conditioning, windows, fragrance and other in-vehicle environmental parameters can be adjusted, etc.; when the corresponding emotional changes are matched, the matching in-vehicle control parameter scene is called to enhance the in-vehicle passenger experience.

[0048] The in-vehicle call processing method provided by the present invention can effectively reduce non-human audio noise interference in the car when making a voice call through a vehicle-mounted device, and even reduce human audio interference from non-calling parties, while protecting the privacy in the car and improving the call quality. In addition, during the voice call, other audio in the car will not be interrupted, thereby improving the user experience and comfort, and will not incur additional hardware costs or modification costs.

[0049] Example 2 The present invention also provides a vehicle-mounted call voice processing system, which executes the vehicle-mounted call voice processing method provided in embodiment 1. Figure 2 Schematic diagram of a vehicle call voice processing system provided by an embodiment of the present invention, specifically comprising: Audio receiving device: used to receive mixed audio; Audio processing module: used to obtain the current in-vehicle call mode when the in-vehicle call is connected; the in-vehicle call mode includes a non-privacy call mode and a privacy call mode; according to the current in-vehicle call mode, select a target playback device for the call audio from the playback devices in the car, and control the target playback device to play the call audio; if the current in-vehicle call mode is a privacy call mode, obtain the current call encryption level; according to the current call encryption level, control the second playback device to play content matching the encryption level; Playback device: used for playing audio; the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person talking in the car is smaller than the distance between the second playback device and the person talking in the car.

[0050] Each part in the present application can be embedded in the existing vehicle-mounted equipment without major modification, thus reducing the cost of equipment upgrade.

[0051] Example 3 Figure 3 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 500 includes one or more processors 501 and a memory 502 .

[0052] The processor 501 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 500 to perform desired functions.

[0053] The memory 502 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 501 may run the program instructions to implement a vehicle call voice processing method and / or other desired functions of any embodiment of the present application described above. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0054] In one example, the electronic device 500 may further include: an input device 503 and an output device 504, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown). The input device 503 may include, for example, a keyboard, a mouse, etc. The output device 504 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 504 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0055] Of course, to simplify, Figure 3 Only some of the components related to the present application in the electronic device 500 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 500 may also include any other appropriate components.

[0056] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute a method for in-vehicle call voice processing provided by any embodiment of the present application.

[0057] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0058] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes a method for in-vehicle call voice processing provided by any embodiment of the present application.

[0059] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0060] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0061] It should also be noted that the orientations or positional relationships indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing vehicle-mounted call voice, characterized in that: include: When a car call is connected, obtain the current car call mode; The in-vehicle call mode includes a non-privacy call mode and a privacy call mode; According to the current in-vehicle call mode, a target playback device for the call audio is selected from the playback devices in the vehicle, and the target playback device is controlled to play the call audio; wherein the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person who is talking in the vehicle is smaller than the distance between the second playback device and the person who is talking in the vehicle; If the current in-car call mode is the private call mode, obtain the current call encryption level; According to the current call encryption level, controlling the second playback device to play content matching the encryption level; According to the current in-vehicle call mode, a target playback device for the call audio is selected from the playback devices in the vehicle, in the following method: If the current in-vehicle call mode is a private call mode, using a first playback device to play the call audio; When the current in-vehicle call mode is a non-privacy call mode, the call audio is played using the first playback device and / or the second playback device.

2. The method for processing vehicle-mounted call voice according to claim 1, characterized in that: Before controlling the target playback device to play the call audio, the method further includes adjusting the volume of the playback device according to the caller's emotions, call keywords, and response level, specifically: Acquire the emotions of the caller through the voice emotion recognition model; Use neural network model to model conversation keywords and response level; Adjust the volume of the playback device according to the caller's mood, call keywords and response level.

3. The method for processing vehicle-mounted call voice according to claim 1, characterized in that: Before controlling the target playback device to play the call audio, the method further includes: performing call audio extraction processing on the transmitted mixed audio, and performing aliasing reconstruction processing on the call audio after the call audio extraction processing in a non-privacy call mode.

4. The method for processing vehicle-mounted call voice according to claim 3, characterized in that: The method for extracting the call audio from the transmitted mixed audio is as follows: Perform noise reduction on the incoming mixed audio; Separate the human voice audio from the mixed audio after noise reduction processing; Perform keyword recognition on the human voice audio, and retain the sentence audio containing the voice call keywords; Perform voiceprint feature recognition on the sentence audio containing the voice call keywords, and output the voiceprint features of the caller; The call audio is extracted according to the voiceprint feature.

5. The method for processing vehicle-mounted call voice according to claim 4, characterized in that: The method for separating the human voice audio from the mixed audio after the noise reduction process is as follows: Input the noise-reduced mixed audio into the trained separation model and output the human voice audio; The separation model is used to extract human voice audio from a variety of mixed audios.

6. The method for processing vehicle-mounted call voice according to claim 3, characterized in that: The method of performing aliasing reconstruction processing on the call audio after the call audio extraction processing is as follows: The call audio extracted and processed by the call audio is reconstructed by aliasing with the audio being played in the car before the in-car call is turned on, and the aliased and reconstructed audio is then played through the target playback device.

7. The method for processing vehicle-mounted call voice according to claim 1, characterized in that: The method of controlling the second playback device to play content matching the encryption level according to the current call encryption level is: When the current call encryption level is level one, controlling the second playback device to play entertainment audio; When the current call encryption level is level 2, controlling the second playback device to play interference audio; The interference audio is entertainment audio whose voiceprint features are consistent with the voiceprint features of the caller.

8. A vehicle-mounted call voice processing system, characterized in that: The in-vehicle call voice processing method according to any one of claims 1 to 7 specifically comprises: Audio receiving device: used to receive the mixed audio; Audio processing module: used to obtain the current in-vehicle call mode when the in-vehicle call is connected; the in-vehicle call mode includes a non-privacy call mode and a privacy call mode; according to the current in-vehicle call mode, select a target playback device for the call audio from the playback devices in the car, and control the target playback device to play the call audio; if the current in-vehicle call mode is a privacy call mode, obtain the current call encryption level; according to the current call encryption level, control the second playback device to play content matching the encryption level; Playback device: used for playing audio; the playback device includes a first playback device and a second playback device; the distance between the first playback device and the person talking in the car is smaller than the distance between the second playback device and the person talking in the car.

9. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the steps of the in-vehicle call voice processing method as described in any one of claims 1 to 7 by calling the program or instructions stored in the memory.

10. A storage medium, characterized in that: The storage medium stores a computer executable program, which is called by a processor to execute the steps of the in-vehicle call voice processing method according to any one of claims 1 to 7.

Images